If you're a few years old like me, I think you'll be a lover of the aesthetics of old CRT terminals as a good retro lover that we are. Cool-Retro-Term emulates it very well and I'm sure you already know it.

brew on macOS installs it without problems, but only for Intel x86_64 using Rosetta 2, which adds an emulation layer that can affect performance. I've tried it and it's not that noticeable, but if you have an Apple Silicon (M1, M2, M3) computer and you want to get the most out of it, the ideal is to have a native version for aarch64, don't you think?

Well, today I have compiled it for aarch64 and I leave it here in case you are interested. I have refactored some warnings that came out when compiling, but in general everything works perfectly following the steps that you can read in the GitHub repository here. I hope you enjoy it and let me know if you find any bugs.

Link: Cool-Retro-Term for aarch64

I've been working for months on a project that uses AWS Lambda + Python + FastAPI + Docker. I tried to debug a Lambda following several tutorials, AI, Medium articles, and YouTube videos without success. Almost all of them were obsessed with using AWS SAM, which I don't use at all. So I took advantage of a quiet Sunday afternoon in my dungeon (I mean basement), and finally found a way to make it work. I'll show you how below and I hope it helps you. 😉

Ah!... The wonderful world of security, especially in the realm of containers, which has seen a boom in the adoption of tools to detect vulnerabilities. Among my favorites is Trivy, which stands out as a versatile and powerful scanner, and today I'll show you how to use it.

The articles I've read out there are somewhat outdated or AI-generated, and it pains me, mostly because we developers can't live ignoring security without having to take a cybersecurity course, right? Well, let's get to it.

What is Trivy? 🤷

• But I don't know what Trivy is...
• Patience, young Padawan. I'll tell you.

Trivy is an open-source tool developed by Aqua Security, renowned for its speed and simplicity in detecting vulnerabilities in container images, file systems, application dependencies, etc. You don't need to know more. There are many vulnerability scanners: Chimera, Clair, Snyk,... but I was looking for one that was easy to use and didn't give me problems. I've been using this one for years and it works great for me.

How to install it? 📦

Well, it offers several installation methods depending on the operating system and user needs. I'll refer you to their GitHub so you can see the available download versions. I'll comment on the way I install it on macOS:

macOS (with Homebrew):

brew install aquasecurity/trivy/trivy

You can also do it using Docker, by the way, I use a lighter client on macOS called OrbStack:

docker run aquasec/trivy image <image_name>

Couldn't be easier. 😉

How to use Trivy locally? 💻

It allows scanning different types of targets:

• Container images:

trivy image image_name:tag
trivy image alpine:3.15 # Example

• File system or directories:

It will scan the current directory for vulnerabilities in dependencies and sensitive files.

trivy fs .
trivy fs --scanners vuln,secret,misconfig . # Scans for vulnerabilities, secrets, and misconfigurations

• Application dependencies:

Automatically detects files like requirements.txt|pyproject.toml|uv.lock (Python), package.json (Node.js),...

trivy config path/to/file

Configuration and customization 🔧

Although what I've explained is enough, it allows customizing its behavior through a configuration file. You can create a .trivyignore file to exclude certain files or directories from the scan (similar to a .gitignore, indeed). You can also use a trivy.yaml file to define specific configurations like the severity level to report.

ignore:
    - path/to/ignored/file
    - path/to/ignored/directory

You have different options to adjust its behavior using flags like --severity, --format, --output, and environment variables starting with TRIVY_ (like TRIVY_SEVERITY=CRITICAL).

Tips and best practices 📚

• Review the arguments you can pass via the Terminal to customize the scan.
• Always scan before uploading images to a registry to prevent vulnerabilities, especially, from reaching production.
• Use the --exit-code flag to automatically break insecure builds in CI/CD pipelines. I mention it but I don't use it. It's good to warn about vulnerabilities, but it's not always necessary to break the build.
• Automate periodic scanning of already deployed images to detect new vulnerabilities.
• Customize reports using output formats (table, json, sarif, etc.) according to your needs, although the console results are sufficient for me.

Conclusions 📝

For me, it was a great discovery years ago, as it stands out for its ease of installation and use. It allows detecting vulnerabilities of very different types as I mentioned, and helps you strengthen the security of your projects without adding complexity that is sometimes unnecessary.

I decided to mention it because I have colleagues who didn't know about it, and I find it a very useful tool for any developer.

I hope this helps you, and if you have any questions,... Here I am! 😉

I'm currently working in a project that explores the capabilities of GenAI architecture and its applications in various fields. We are using high level resources like AWS and its services like Bedrock, Lambdas, StepFunctions and others to create a robust and scalable architecture (That is what we say).

This is OK for a high-level architecture where you can use all those expensive services, but... What if you want to create a low/mid-level AI project that can be used in any environment? Amy Chen contacted with me to present TensorZero, and today I'm going to show you how I use it in a little example.

What is TensorZero?

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models. It's a black box that allows you to create and train your own models without the need for expensive resources. It's designed to be easy to use and integrate into your existing projects... And yes before you ask: It's open-source and some of its components are written in Rust.

• Integrate our model gateway.
• Send metrics or feedback.
• Optimize prompts, models, and inference strategies.
• Watch your LLMs improve over time.

So at the end, it provides a data & learning flywheel for LLMs by unifying:

• Inference: one API for all LLMs, with <1ms P99 overhead.
• Observability: inference & feedback → your database.
• Optimization: from prompts to fine-tuning and RL.
• Experimentation: built-in A/B testing, routing, fallbacks.

So cool, right? But how do you use it? Let's see a simple example of how to use it in your own projects.

How to use TensorZero

I'm going to test the TensorZero library with an example that generates a pseudo-summarizer. The idea is to create a simple function that tell us what TensorZero is. The function will be called generate_summarizer and will use the gpt-4o-mini model.

So according to the Quick Start documentation, I need a file called tensorzero.toml with a minimal setup:

# A function defines the task we're tackling (e.g. generating a summarizer)...
[functions.generate_summarizer]
type = "chat"

# Since we only have one variant for this function, the gateway will always use it.
[functions.generate_summarizer.variants.gpt_4o_mini]
type = "chat_completion"
model = "openai::gpt-4o-mini"

Oh! You need to set/export an environment variable for OPENAI_API_KEY with your API key.

Now grab the next docker-compose.yaml file and run it:

docker-compose up

You can interact with the TensorZero Gateway in several ways: using the TensorZero Python client, leveraging existing OpenAI clients (available for Python, Node.js, and other languages), or directly through its HTTP API, making it accessible from any programming language.

I'm going to use the basic Python implementation, so I need to install the tensorzero package. Let's do it using uv, but you can use any package manager you want. So open a new terminal and run the following commands:

uv init .
uv add tensorzero

Now I can create a simple script to generate a summarizer. The script will look like this and It must to have the name after.py:

from tensorzero import TensorZeroGateway

with TensorZeroGateway.build_embedded(
    clickhouse_url="https://chuser:chpassword@localhost:8123/tensorzero",
    config_file="config/tensorzero.toml",
) as client:
    response = client.inference(
        function_name="generate_summarizer",
        input={
            "messages": [
                {
                    "role": "user",
                    "content": "Summarize the key features of TensorZero.",
                }
            ]
        },
    )

print(response)

Now run the script:

export OPENAI_API_KEY=your_openai_api_key
uv run after.py

This is the output you get:

ChatInferenceResponse(
    inference_id=UUID('0195e199-9227-76b3-a96b-f042cf892917'),
    episode_id=UUID('0195e199-9227-76b3-a96b-f05bb3aec0d3'),
    variant_name='gpt_4o_mini',
    content=[
        Text(
            type='text',
            text='TensorZero is an advanced machine learning platform designed to accelerate the development and deployment of AI models. Here are the key features:\n\n1. **Model Development**: TensorZero offers intuitive tools for building and training machine learning models, making it accessible to users with varying levels of expertise.\n\n2. **Scalability**: The platform is designed to handle large datasets and complex models, enabling users to scale their projects efficiently.\n\n3. **Interoperability**: TensorZero can seamlessly integrate with various data sources and existing frameworks, allowing for flexibility in workflow and data management.\n\n4. **Real-time Collaboration**: It supports collaborative features, enabling teams to work together in real time on projects.\n\n5. **Monitoring and Visualization**: The platform includes tools for monitoring model performance and visualizing data, which helps in understanding and optimizing models.\n\n6. **Deployment Options**: TensorZero provides various deployment options, facilitating the launch of models in different environments, whether on-premises or in the cloud.\n\n7. **User-friendly Interface**: A user-friendly design simplifies navigation and enhances the user experience, catering to both novice and experienced users.\n\n8. **Customizable Workflows**: Users can create customized workflows to fit specific project needs, enhancing efficiency and productivity.\n\nTensorZero aims to streamline the machine learning lifecycle, from development to deployment, while ensuring ease of use and adaptability.',
            arguments=None
        )
    ],
    usage=Usage(
        input_tokens=17,
        output_tokens=276
    ),
    finish_reason=<FinishReason.STOP: 'stop'>
)

Not bad! The summarizer is working and you can see the output in the terminal. You can also see the input and output tokens used in the request. This is useful for monitoring and optimizing your usage of the OpenAI API. You can also see the inference ID and episode ID, which are useful for tracking the requests and responses in the TensorZero system.

Do you remember the Docker container we started? Go to http://localhost:4000 and you can see the TensorZero UI dashboard.

We can access the Observability and Optimization tabs. The Observability tab shows the Inferences, Episodes, and Functions. The Optimization tab shows an interesting feature: Supervised Fine-tuning. This super-power allows you to improve the performance of your model by providing it with additional info as you can see above. Once we start using more advanced functions like feedback and variants, the observability UI will enable us to track metrics, experiments (A/B tests), and more.

This was only a call to its library as you can see. You have more tutorials (A Chat bot!) in the TensorZero documentation, where you can explore more features and functionalities.

Final Words

This example is a tiny taste of what TensorZero is capable of. I hope to get time to go deep into its features and functionalities in the future. 💪

I said you can build low/mid-level projects with it, but I think you can also build high-level projects with it, too. It allows you to create and train your own models without the need for expensive resources, and this is a great advantage for developers who want to create their own AI applications without the need for expensive cloud services. I like that it’s designed to be easy to use and integrate into new or existing projects, so... What are you waiting for? Go ahead and try it out! You can find the documentation here.

Thanks again to Amy Chen for show me TensorZero. I hope you find this article useful and that it helps you to create your own AI applications with TensorZero. If you have any questions or comments, feel free to reach out to me on X-Twitter/LinkedIn/Email.

A webhook (also known as reverse API) is a tool that allows a system or application to send notifications about specific events to another system or application in real-time.

Define route in our application

The application will define the route where the webhook will listen for stripe events.

@app.route('/webhook', methods=['POST'])
    def stripe_webhook():
        return webhook.webhook()

The webhook method will handle stripe events. It must be implemented to handle the desired events. You can see an example at: https://stripe.com/docs/webhooks#webhook-endpoint-integration.

Stripe CLI

Stripe CLI is a developer tool that helps create, test, and manage Stripe integration directly from a terminal

1. Installing Stripe CLI:

For Windows:

1. Download the latest windows tar.gz file from https://github.com/stripe/stripe-cli/releases/latest
2. Unzip the stripe_X.X.X_windows_x86_64.zip file
3. Run the uncompressed .exe file

For GNU/Linux or macOS:

1. Download the latest linux tar.gz file from https://github.com/stripe/stripe-cli/releases/latest
2. Unzip the file: tar -xvf stripe_X.X.X_linux_x86_64.tar.gz
3. Add ./stripe to your execution path.

2. Login to Stripe CLI

Use the stripe login command to authenticate to Stripe CLI in your browser. This command generates a restricted key set for your account (one in test mode and one in active mode) that is valid for 90 days.

$ stripe login
> Your pairing code is: glitz-boom-entice-quiet
> This pairing code verifies your authentication with Stripe.
> Press Enter to open the browser or visit <url> (^C to quit)

Optionally, if you don't want to use a browser, use the --interactive flag to authenticate with an API secret key or a restricted key.

$ stripe login --interactive

Optionally, you can use the --api-key flag to specify your API secret key inline each time you send a request

$ stripe login --api-key <stripe-test-api-key>

3. Sending events from Stripe CLI

The Stripe client allows us to send events to simulate the different operations that Stripe notifies. First, you must indicate the route where our application will handle Stripe events

$ stripe listen --forward-to http://127.0.0.1:5000/webhook

To get the list of possible events, run the following command:

$ stripe trigger

To send a specific event, run the following command:

$ stripe trigger <event_name>

4. List of required events

Studying the webhook, the most common events when making a payment are (from bottom to top):

transfer.created
payment_intent.succeeded
charge.succeeded
charge.pending
payment_intent.processing
payment_intent.created
payment_intent.requires_action
customer.subscription.updated
invoice.created

Others interesting events:

customer.updated
customer.subscription.deleted
customer.subscription.updated
invoice.updated
invoice.voided
invoice.paid
invoice.finalized
subscription.triggered
invoice.draft.paid

It never hurts to remember the basic Git commands, and today is that day. In this article that I wrote for my team at one of the companies where I worked, I'll show you how we worked with this version control system on a project that involved six people and almost two years of development.

What to Know About Branches?

I usually work using GitFlow, where we have a main branch, a develop branch, and others that can be feature/ or hotfix/.

The flow is always the same: from develop, new branches are created to work locally and then merged back into develop (remote). When we have reached our goals, develop is merged into main to go into production.

If you are new to Git, I recommend that you first read the article Introduction to Git.

Naming Conventions

Regarding the standard for naming commits, I have recently been using Conventional Commits, which is a standard for writing commit messages that you can see at this link. Here is the format and the most common types:

<type>[optional scope]: <description with verb in infinitive>

feat: add new functionality
fix: fix a bug
docs: changes in documentation
style: changes that do not affect the meaning of the code (whitespace, formatting, missing semicolons, etc.)
refactor: a code change that neither fixes a bug nor adds a feature
perf: a code change that improves performance
test: add missing tests or correct existing tests
chore: changes to the build process or auxiliary tools and libraries such as documentation generation

Git File Lifecycle or States

The most relevant states (there are several more) are:

• Untracked Files: these are files that DO NOT live inside Git, only on the hard drive. Git has no record of their existence. For example, a new file that we have created and has not yet been added with git add.

touch my_new_file # untracked

• Staged Files: these are files in Staging. They live inside Git and there is a record of them because they have been affected by the git add command, although not their latest changes. Git already knows about these latest changes, but they have not yet been definitively saved in the repository because the git commit command is missing.

git add my_new_file # staged

• Tracked Files: these are the files that live inside Git, have no pending changes, and their latest updates have been saved in the repository thanks to the git add && git commit commands.

git commit my_new_file # tracked

Initializing a Project

The first step is to initialize the project. This is done the first time by following a series of steps. The easiest way to do this is to create the project on your Git server (remote/local Docker container, GitLab, GitHub, etc) and download it to our system.

It's recommended to install the Git Flow package. We execute the following, which gives you the default values:

git flow init -d
git branch -m master main # Change the name of the master branch to main if desired

Working with Branches

The first thing we are going to learn is the git status command, which will tell us the current state of the repository, with the changes that need to be made, deletions, or if everything is up to date.

• View local and remote branches:

git branch -a

    develop
    * main
    remotes/origin/HEAD -> origin/main
    remotes/origin/develop
    remotes/origin/main

• Switch to a branch:

git switch develop

    * develop
    main

• To create a branch and switch to it, we have two options. From develop, execute one of the following options:

# Option 1
git branch feature/api-token && git switch feature/api-token
# Option 2
git switch -c feature/api-token

develop
* feature/api-token
main

• Delete a branch:

git checkout develop && git branch -D feature/api-token # D = force delete or -d = safe delete and warns if there are changes

We can also delete remote branches:

git push origin --delete feature/api-token

origin is a convention that refers to the remote repository.

If we want to delete a branch with changes in staging, it may not allow us to delete it. There are several methods. I prefer moving the changes to the stash (a kind of clipboard or temporary memory) that "cuts" all the changes and deletes the branch. The other method is more drastic and deletes all changes made in that branch since it was created:

git stash -u
git checkout develop
git branch -D branch_name

Essential Git Commands

git clone

git clone repository_URL

git fetch

This command downloads the remote content but does not update the local repository's working state, so your current work will not be affected. Similar to the svn update command.

git fetch
git fetch -a -p # for all branches (all) and removes (prune) local branches that no longer exist remotely

If you want to know more about this command, read the article: git fetch.

git add

Add file(s) to the staging area:

git add README.md
git add .
git add -a # All changes.
git add -A # New, modified, and deleted files.
git add --ignore-removal . # New and modified files.
git add -u # Modified and deleted files.

Difference between git add ., git add -a, and git add -A

• git add .: Adds all new and modified files in the current directory and its subdirectories, but does not include deleted files.
• git add -a: Adds all new, modified, and deleted files in the current directory and its subdirectories.
• git add -A: Adds all new, modified, and deleted files in the entire repository, both in the current directory and anywhere else in the repository.

git stash

Temporarily saves changes to bring them back later.

git stash # It's like cutting to Git's clipboard
git stash -u # Also saves untracked files.
git stash pop # It's like pasting the last stash from Git's clipboard
git stash save "message" # Saves changes with a message
git stash list # shows what we have in the stash
git stash pop stash@{2} # Recovers from stash with index 2

By default, changes in stash will become staged. If you want to remove them, use the git restore --staged command.

More info on Stash at the following link: Git stash.

git pull

Fetches data from the remote repository and then merges the changes with the local repository. It's the same as doing git fetch && git merge origin/$CURRENT_BRANCH

git pull -p # -p=prune, removes references to deleted remote branches
git pull --force # overwrites the current local branch

git push

Push local changes to remote.

git push # -p=prune, removes references to deleted remote branches
git push --force # overwrites the remote branch with the same name

Regarding the --force parameter, be very careful and use it only when you know exactly what you are doing.

git rm

Remove files marked as tracked. Better to use git rm than rm to avoid problems.

git rm file_name

git merge

Case 1: DO NOT want to keep local changes. Maybe you modified a file to test, but you no longer need the modification. The only thing that matters is being up to date with remote changes.

git fetch
git reset --hard HEAD
git merge origin branch_name # usually develop. @{u} is the same as origin $CURRENT_BRANCH

Case 2: You care about local changes:

git fetch
git pull origin develop
# Resolve conflicts if any

git log

Shows a history of all branches:

git log
git log --oneline --decorate --graph
git log --pretty=format:'%h - %an, %ar : %s'

.gitconfig File

~/.gitconfig or ~/.config/git/config is where the git configuration is on your computer. From there, we can, for example, create aliases for a list of commands that we usually use so we don't have to type the same thing all the time.

Some useful commands:

git config --global user.name "John Doe"
git config --global user.email john_doe@dev.com
git config --global core.editor "code --wait" # VSCode as default editor
git config --global -e # Opens .gitconfig file for editing
git config --global core.autocrlf [true, input] # true for Windows / input for Mac/Linux
git config -h # Help on config

# .gitconfig file

[alias]
    pull_force = !"git fetch --all; git reset --hard HEAD; git merge @{u}"

Example of Daily Workflow for Working with Git

Let's see an example of how to work with Git on a project. Let's imagine we are going to work on a new feature that involves authenticating an API.

Although my team and I work with common Git commands, I'll also show how it would be done with GitFlow.

1. Create feature branch

We create a branch parallel to develop where we will work. Generally, using GitFlow it will be a feature/ branch, for example:

git fetch -a -p
git switch develop # In case we are on another branch, you can check where you are with git branch
# Common mode
git switch -c "feature/#HM-01-auth-api"
# GitFlow mode
git flow feature start HM-01-auth-api

2. Add commits

We have worked on the necessary changes, so we will add them to the stage and then commit:

git status # to know which files are modified, untracked,...
git add . # or better the names of the files for that commit
git commit -m "feature/#HM-01-auth-api"

Regarding the use of git add ., It's considered bad practice, as we can unintentionally introduce unnecessary files. Also, commits are usually made according to the files needed for a logic to work and It's easier when doing a code review. For example, if we need to authenticate an API in our task, the correct way would be:

git add auth/api_auth.py app.py
git commit -m "feature/#HM-01-Add new class & modify routes" # Message text in English and does NOT end with a period
git add readme.md
git commit -m "feature/#HM-01-Update doc" # Verbs in infinitive: add, merge, bump, change, delete, modify, fix,...
git add test/system/api/auth/test_api_auth.py
git commit -m "feature/#HM-01-Add tests for all routes" # It's advised that the message does not exceed 50 characters

3. Compare with develop

Other developers probably advance in the code and your branch is not up to date. It's necessary to download the new modifications from the develop branch and choose the changes that remain.

# We are in the feature/ branch, if not we switch to it
git fetch -a -p # Not necessary, but always advisable to keep branches up to date
git pull origin develop # IMPORTANT: This downloads changes from remote develop, NOT from your local develop branch.

Now two things can happen, everything is fine (we move to point 4) or there are conflicts that need to be resolved (merge conflict).

3.1. Merge conflict. Resolve conflicts in your branch.

We will review with git status the files that need to be resolved and resolve them one by one. It's recommended to use a graphical application or a more friendly IDE, as our code now contains merge traces that could be forgotten to remove. Some recommended Git apps are Sourcetree, GitKraken.

4. Push changes to the remote git server

We just need to push the changes to merge them with develop. There are three ways to do this: git merge, git rebase, and the gitflow way.

# Common mode
# We are in the feature/ branch. If not, we switch to it
git merge origin develop --fast-forward # Option 1
git merge origin develop --squash # Option 2

git rebase origin develop && git merge --fast-forward # Option 3

# GitFlow mode
git flow feature finish HM-01-auth-api

The recommended way is to use git merge, although I'll explain the two options:

• With git merge we combine the commits and make a new commit in develop. If the develop branch is very active, this option can "contaminate" the history quite a bit.

• With git rebase, WE DELETE the commits from the feature branch, equalize with develop, and put new commits on top. The merge would be done with git merge --fast-forward.

• It should be clear that git rebase solves the same problem as git merge: they are designed to integrate changes from one branch to another, but in different ways. git rebase is mainly used so that in the Git history, branches other than main and develop of the development team (features, hotfix) are not seen, as these parallel branches may not be of interest in the history or if there are many commits and they want to be reordered (5 commits can be merged into 2, for example), we would have the option to use an interactive rebase with git rebase -i. It's all a matter of aesthetics when we run git log.

• Another golden rule of git rebase is NEVER USE IT ON PUBLIC BRANCHES.

More information at atlassian.com > merging-vs-rebasing

Tips and Other Commands

untrack a file

git rm --cached file_name

Fix a bug in main

To do this, create a hotfix/xxx branch locally to fix the problem and merge it into main. If everything is correct, we must also merge it with develop. Using gitflow, you need to run the following command:

git flow hotfix start HM-01-fix-bug
# Do your Kung-Fu
git flow hotfix finish HM-01-fix-bug

Get remote changes without keeping local changes

You want to delete all uncommitted local changes. Maybe you modified a file to test, but you no longer need the modification. The only thing that matters is being up to date with the remote branch.

git fetch -a
git stash -u # Optional but advisable
git reset --hard HEAD
git merge --no-ff origin develop # Or alternatively we can do git pull

Delete my changes

If you want to revert to the previous state:

git reset --soft # Keeps changes
git reset --hard # Deletes even your code. Use with caution

Go to a previous state via an ID without keeping changes

git log # See the commit ID to which we want to revert
git reset --hard 23j45b3b45hb345b

Interesting Links

• Git Guide
• Learn Git Branching
• Git for Beginners: The Definitive Practical Guide
• git-scm.com
• Explain Git with D3
• Freecodecamp > #Git
• The stacking workflow

I might take the PCEP exam to demonstrate my knowledge in Python. For now, I have taken a CISCO course called Python Essential 1 and here are some notes, curiosities, and code that I found interesting if you are not a Pythonista.

Quick notes

• CPython is the default and reference implementation of the Python language, written in C. When you install Python on your system, you are actually installing CPython. 😱
• PEP (Python Enhancement Proposals) is a system for designing and specifying Python. PEPs are documents that describe and discuss proposed features and changes for Python.
• What are the four fundamental elements of a language? An alphabet, a lexicon, a syntax, and a semantics.
• Where do functions come from? From Python itself (built-in functions), from modules, or from your code.
• 0o123 is an octal number (base 8). They start with 0o and this example is equal to 83 in decimal (base 10).
• 0x123 is a hexadecimal number (base 16). They start with 0x. 291 is the decimal result in this case (base 10).
• .4 = 0.4 | 4. = 4.0
• The result produced by the division operator is always a float, even if the operands are integers and the result is an integer. print(10 / 5) # 2.0
• The asterisk (_) sign, when applied to a string and a number (or a number and a string) becomes a replication operator: "an-" _ 3 # an-an-an-
• What is the default return value for a function that does not explicitly return any value? It returns the value None.
• What is the result of the following comparison? 2 == 2.. The answer is True. Python converts the integer to a float before comparing them.
• Useful exceptions: ValueError, TypeError, AttributeError, SyntaxError.

What happens when Python encounters an invocation like the one below?

function_name(argument)

• First, Python checks if the specified name is legal (it explores its internal data to find an existing function of that name; if this search fails, Python aborts the code).
• Second, Python checks if the function's requirements for the number of arguments allow it to invoke the function in this way (for example, if a specific function requires exactly two arguments, any invocation that provides only one argument will be considered erroneous and will abort the code execution).
• Third, Python leaves the code for a moment and jumps into the function to be invoked; therefore, it also takes the argument(s) and passes them to the function.
• Fourth, the function executes the code, causes the desired effect (if any), evaluates the desired result(s), and completes the task.
• Finally, Python returns to the code (to the place immediately after the invocation) and resumes its execution.

Sequence types and mutability

Lists = []

list1 = [3] * 3 # [3, 3, 3]
list2 = [3, 3, 3] # [3, 3, 3]
list3 = [3 for i in range(3)] # [3, 3, 3]

We have three different ways to generate a list in Python

• Lists are mutable (they can be modified).
• They are sequences (they can be indexed and sliced).
• They are heterogeneous (they can contain elements of different types).
• They are ordered (the order of elements is important).
• Lists can be nested (a list can contain other lists).

Tuples = ()

my_tuple = (1, 2, 3)

• Tuples are immutable.
• They are sequences.
• They are heterogeneous.
• They are ordered.
• Tuples can be nested.

Dictionaries = {}

dictionary = {"cat": "chat", "dog": "chien", "horse": "cheval"}

• Dictionaries are mutable.
• Dictionaries are not sequences.
• Dictionaries are heterogeneous.
• Dictionaries are not ordered.
• Dictionaries can be nested.

my_dict = {"key1": "value1", "key2": "value2"}
my_dict["key3"] = "value3"

for key in my_dict.keys():
    print(key, "->", my_dict[key])
# key1 -> value1
# key2 -> value2
# key3 -> value3

dictionary = {"cat": "chat", "dog": "chien", "horse": "cheval"}
for key in sorted(dictionary.keys()):
    print(key, "->", dictionary[key])
# horse -> cheval
# cat -> chat
# dog -> chien

del dictionary['dog']

Questions and answers

• What is the output of the following code?

a = 1
b = 0
x = a or b
y = not(a and b)
print(x + y)
# 2

The expression a or b evaluates to 1 because in Python, the or operator returns the first truthy value it encounters. Since 1 is truthy, x = 1.

The expression a and b evaluates to 0 because b is falsy (0). The and operator returns the last value if both values are truthy, otherwise it returns the first falsy value encountered. Hence, a and b gives 0. not(0) evaluates to True, which in Python is equivalent to 1. Therefore, y = 1.

EXTRA!: Cool code

Print() arguments

print("Hello", "World", sep="***", end="!")
# Hello***World!

Sorting a list

my_list = [8, 10, 6, 2, 4]  # list to sort
swapped = True  # We need it to be true to enter the while loop.

while swapped:
    swapped = False  # no swaps so far
    for i in range(len(my_list) - 1):
        if my_list[i] > my_list[i + 1]:
            swapped = True  # swap occurred!
            my_list[i], my_list[i + 1] = my_list[i + 1], my_list[i]

print(my_list)
# [2, 4, 6, 8, 10]

Protection against iterating through None values

for element in mylist or []:
do_stuff (element)

Explanation: If mylist is None, the loop will iterate through an empty list.

Lists store memory locations

list_1 = [1]
list_2 = list_1
list_1[0] = 2
print(list_2)
# [2]
🤔

You could say that:

• The name of an ordinary variable is the name of its content: variable = 1
• The name of a list is the name of a memory location where the list is stored: list_1 = [1], where list_1 is a memory location name.

list_1 = [1]
list_2 = list_1[:]
list_1[0] = 2
print(list_2)
# [1]

This not visible part of the code described as [:] can produce a completely new list. my_list[start:end] is a way to copy a list.

my_list = [10, 8, 6, 4, 2]
new_list = my_list[1:3]
print(new_list)
# [8, 6]

The new_list will contain end - start (3 - 1 = 2) elements ‒ those with indices equal to 1 and 2 (but not 3).

my_list = [10, 8, 6, 4, 2]
new_list = my_list[3:]
print(new_list)
# [4, 2]

Interesting Links

• Medium > Most Developers Failed with this Senior-Level Python Interview Question

As a developer, you will most likely have done a project, and had to use a relational database. It happens all the time on each project. I think I miss very few relational DBMS (Database Management System) that I haven’t used in my profile as DevOp. This has not been the case for non-relational BBDD or also called NoSQL (Not Only SQL) such as MongoDB. I will explain the differences above and in a future article, we will see their use.

Relational Databases

Main Features

1. Tabular structure: The data is organized in tables with rows and columns, where each row represents a record and each column an attribute of the record.
2. Fixed Schema: Require a predefined schema that determines the structure of data before it can be stored.
3. SQL language: Use SQL (Structured Query Language) for data manipulation and query.
4. ACID properties: Atomicity, Consistency, Isolation and Durability, which ensures reliable and consistent transactions.

Pros

• Consistency and Security: Ideal for applications that require secure and consistent transactions, such as financial systems.
• Data Integrity: Thanks to the ACID properties, the integrity and consistency of the data is ensured.
• Tools and Support: Wide availability of tools and support due to its long history in the market.

Cons

• Vertical Scalability: Generally they scale better vertically (increasing server capacity) than horizontally (adding more servers).
• Scheme Rigidity: Less flexible to changes in data structure, which may make it difficult to adapt to new needs.

Examples and where you could use it

Relational databases are often used in applications that require primarily transactional systems, where data consistency and integrity are critical and the data have a fixed, well-defined structure. Examples: MySQL/MariaDB, PostgreSQL, Oracle, SQL Server. You can use them in banking systems, inventory management, reservation system, CRM,...

NoSQL Databases

Main Features

1. Dynamic Schema: Do not require a fixed schema, allowing for storing unstructured or semi-structured data.
2. Various Data Models: They include several types such as key-value, documents, columns and graphs.
3. Scale Out: Designed to scale easily by adding more nodes to the system.
4. Eventual consistency: Often prioritise availability and partitioning tolerance over immediate consistency, following the CAP theorem.

Pros

• Flexibility: Can handle data of different types and structures without the need for a predefined schema.
• Scalability: Scale horizontally efficiently, ideal for applications with high data volumes and high availability needs.
• Performance: They offer high performance in read and write operations.

Cons

• Less Consistency: In many cases they offer instant rather than instant consistency, which may not be suitable for all applications.
• Less Support Tools: Although this is changing, they have historically had fewer tools and support compared to relational databases.

Examples and where you could use it

They are perfect for Big Data and real-time analytics as they support fast access to large volumes of data and the data does not necessarily have to be fixed in structure. Examples: MongoDB (documents), Cassandra (columns or tabular), Redis or Amazon DynamoDB (key-value). The most common use of this type of database is for location, geospatial/streaming/messaging/transaction/inventory data, customer profile, vector embeddings,...

When to choose one or the other?

Obviously, it will be defined by the project you must accomplish. There are no winners or victors, and each one is born with a purpose. I have given you some examples and use cases, but experience will show you which is the most suitable. If you have any questions, you can contact me and I will help you choose which database to use, but if we have to order food, then you choose. 😆

Interesting links

• (FREE) Introduction to NoSQL Databases: https://www.coursera.org/learn/introduction-to-nosql-databases

I hate technical interviews like everyone else. But there is SOMETHING I like about them: the questions I haven't previously asked myself. Usually, there's no time to develop an answer that one likes, you know how perfectionist I am. One of them was this week:

"What advantages do you see in Python over PHP?".

I found it interesting and decided to write an article about it from a broad and not very technical perspective.

If you are a macOS user in Spain and need to access through Safari some page where the digital certificate is required, you may have had problems with AutoFirma. Come in and see how to fix the most common errors that occur when trying to access pages where a certificate is required in Safari on macOS Sonoma. Go ahead!.

I don’t tell you a lie when I advise you that if you’re not using AI in your day-to-day life, you’re missing a great opportunity.

WE CAN'T ESCAPE!.

This is moving fast and you do not need to be convinced that it can help you in all the processes you perform, in the profession you have. In this article, I'll tell you how I use it as a developer and maybe in another article, as a writer.

GitHub Copilot

I’m not going to spend much time telling you what I write in this section either. For $20 you have an assistant on your IDE that helps you write code. It’s not perfect by the way, but it saves you time and I'm impressed with the Wow 😱 effect.

Sometimes, it even gives you solutions you hadn’t thought of (and at first it makes you angry as a human that you are). It’s like the smart-ass dude who’s correcting you and giving you solutions without asking him... Funny that I came to mind Eddie Deezen acting in the movie WarGames.

Not everything is as beautiful as it seems, because sometimes it gives you solutions that are not the most optimal, and you have to review them (there are hundreds of memes about this, here is one 😂 ). But hey, that’s what it is this year. The next one, we’ll see...

By the way, in VSCode remember to install the two essential extensions to get the most out of it: GitHub Copilot and GitHub Copilot chat. You also have an extension for use with GitHub Codespaces, which allows you to use Copilot in the cloud.

I recommend looking at the playlists on the Visual Studio Code YouTube channel. I leave you some tips that I use in my day to day:

• Ideal for small scripts: It is one of the features I use most. I have created scripts to automate tasks that took time and now I have them in a snap. For example, a script that cleans the external storage systems before expelling them in Rust (and I don’t have much idea of this language), another that downloads YouTube playlists...

• Make my tests!: What we most hate as programmers, but that helps us to see if what we write meets expectations (and we have not screwed updating a method). Our friend helps you write the tests, but It's not thinking about them. You give him a little push, you’ll see how fast the dirty work does.

• Use keyboard shortcuts: If you use VSCode like me, I recommend that you learn the keyboard shortcuts it offers. Cmd + I to ask him inline, Shift + Cmd + H opens the side chat so you can ask him.

• Use / in the chat: If you type the back / in the chat, it gives you a list of commands that you can use to improve the response. In my case, I use a lot @workspace to give me solutions according to my workspace, but you have many others: /help, #file:index.html, /explain, @vscode, etc.

• Ask what you want: It’s an AI, so don’t be afraid: How can I build this project? How do I install the dependencies? Where are the middlewares? Can you give me the secret to get rich? Remember that if you don’t want generic results, you have to specify @workspace or @file to get solutions that fit your workspace. It is not the same build me a class Calculator that build me in PHP a class Calculator documenting the methods and typing the parameters.

• Errors in the code or Terminal: If you get an error when executing your code, you can ask Copilot what is happening. Select the error and paste it into the chat. If the problem comes from the terminal, select the code, press the right mouse button and choose the Explain this option. You can also click on the stars ✨ that appear on the left of your prompt.

• On your smartphone, too!: If you use GitHub on your smartphone, you can use GitHub Copilot. 😍

• When all fails or doesn’t get the solution you’re looking for: Don’t get upset. What I do is create a new chat and ask again. Above all, it happened to me when he offered you code that comes from some public project. You must specify in the settings within GitHub Copilot that you want to (or not) give you solutions using public code by turning on or off the option Suggestions matching public code (duplication detection filter).

• Let that generate the for your commits: If you don’t like to write comments for commits, tap the stars icon ✨. The good thing is that it is learning from your comments and will give you descriptions according to your style.

Help in the Terminal

When I have to write a command I don’t know or don’t remember, I always go to Warp, the Terminal that has built-in serial AI. It’s like a Copilot for the Terminal and it’s cross-platform. If you haven’t tried it, I recommend it. So write what you want to do and it gives you the solution. Easy and fast... It's free, but it has payment plans.

Code reviews

If you use a GitHub or GitLab account, you can incorporate sourcery into your workflow. In my case, when I go to make a pull request, it gives me suggestions on how to improve my code. For projects open-source is free.

AI agents

Although it is not a tool that I use daily (yet), I find this concept interesting to mention. They explain it very well in this article by Zapier. I'll let my AI explain it to you:

Imagine you have a bot that helps you do repetitive tasks, such as letting you know if a server is down, telling you if a pull request has been approved, or letting you know if an issue has been closed. Well, that’s what AI Agents mean.

You have at Medium a specific topic about it that you can find here. For reference, the AgentGPT project is a good example of what I’m talking about.

If you don’t have time to spend programming these types of agents, your solution may be to use LLM Pipelines, which is a service that allows you to create AI agents without having to program. Check out this article called You Don’t Need an LLM Agent.

Did you hear about Atomic Agents? They are a new type of AI agent that can be used to automate tasks in a more efficient way. You can find more information about them here in Medium or in the official site.

Today I discover SWE Development Kit (swekit). It's a powerful framework for building Software Engineering agents using Composio’s tooling ecosystem. It provides tools like Github, Repo Indexing, Repo Search, File Manager, Shell Manager, and more. It's a good choice if you want to build your own AI agents.

As a learning tool

I think it’s one of the best tools you can have to learn how to code.

In case you are starting with a new language or framework, my advice is to create a markdown file with a header type How to make a CRUD in Python or Introduction to Rust programming. Behold how it begins to give you ideas and sections continuously.

Tell me what you know about my PDFs

I worked as a project manager for the last two years, and I accumulated a lot of reports. If a client requested any data, I had to look for it among hundreds of Word documents or PDFs.

When I found the private-gpt repo, all I had to do was ask for any information from a chat, and it was returned to me along with the name of the file where it was quickly and (almost) effective.

It is a tool that I recommend if you have to deal with many documents and your brain does not remember the commissions that were agreed on six months ago. The best: privately and locally.

Other AI you can use

If you are not convinced or do not want to pay for GitHub Copilot, there are other options.

Two kings actually as an alternative for GitHub Copilot are Cursor and Bolt. The first one has a free plan with 2000 completions per month (not bad) and 50 slow premium requests. The second one is an online IDE, but is a good choice for rapid mockups with predefined templates using Astro, ShaCDN or Vitepress.

Tabnine in its Basic plan, uses autocomplete code and is a GitHub Copilot first cousin. Another approach is DeepCode, which is a code analyzer that helps you find errors and improve your code.

The above-mentioned Sourcery can also help you in this regard and it is very easy to implement it. You can see the documentation for VSCode here.

Do you know Continue? It is a very young extension for VSCode and JetBrains. It seems Copilot, but locally. That is, the model must be supplied by you using Ollama or similar (list of models here). You can get more info here.

There are many sites specializing in AI for developers, such as Phind or Userway, but I recommend those you can use within your IDE, to make it easier to use and "learn" to give you code according to your workspace.

Other I don't tested, but I have heard good things about them are codeium and supermaven.

Final words

It’s funny what happens with this technology: if you don’t use it, you stay behind, and if you use it, it’s like that new co-worker who has put you aside so that you learn everything you know and the company can hire you in the future.

According to some analysts, there is still a lot left for that to happen (five years!), although others believe that it is one more tool and that it will simply modify the way we interact with machines.

Allow me, in the meantime, to enjoy the advantages that it offers me to improve my writing, either of code or of prose, and to continue helping me in those works that take me more time than I would like.

As an example of what I am talking about, I have written the word we, and look at what the autocomplete of Copilot tries to convince me of:

Whatever you say, dude. Whatever you say... 🤦

Recently I got a AOC Model 7Vlr 17" Monitor with VGA connector and I wanted to use it with my Raspberry Pi... The real reason is that I don't have any laptop, PC or device at home with VGA output right now 😅.

I found a cheap adapter on a China store (Under 5 euro-dollar) called VGA 666 (6 bits for Red, 6-Green & 6-Blue), and I'm going to show you how to use it.

So as you can see in the picture above, it's not difficult to connect into the GPIO. No mystery here. Just plug and play.

Now is the time to configure your OS. No matter what you are using, Raspberry Pi OS, Ubuntu, etc. You have to go to the configuration file /boot/config.txt and add/modify/uncomment the following lines:

# Enable DRM VC4 V3D driver
# dtoverlay=vc4-kms-v3d
# max_framebuffers=2

# Comment all hdmi lines

# Comment the next lines
# dtparam=i2c_arm=on
# dtparam=i2s=on
# dtparam=spi=on

dtoverlay=vga666
enable_dpi_lcd=1
display_default_lcd=1
dpi_group=2
dpi_mode=0x9 # See below

Here a list with the most common dpi_mode resolutions I tested, but the best you can do is to search the manual of your monitor to get the correct one. The dpi_mode is a hexadecimal value that defines the resolution and refresh rate. Here are some examples:

HDMI_DMT_SVGA_60 = 0x9 # 800x600 60Hz
HDMI_DMT_1280x800_60 = 0x1C # 1280x800 60Hz
HDMI_DMT_1280x960_60 = 0x20 # 1280x960 60Hz
HDMI_DMT_XGA_60 = 0x10 # 1024x768 60Hz
HDMI_DMT_SXGA_60 = 0x23 # 1280x1024 60Hz

According to the manual of my monitor, I should use as maximum 1280x1024 60Hz. I tried finally with 0x10 and it fits perfectly.

You can find more info here at raspi-config documentation and Legacy config.txt options. The list of dpi_mode is defined in the official forum.

Remember you need to get an output for the audio now!. You can use a 3.5mm jack to speakers, USB sound card or Bluetooth speakers. Check the next parameters in the same file to enable audio output through the 3.5mm jack.

hdmi_force_edid_audio=1
dtparam=audio=on
audio_pwm_mode=1

If you have problems accessing the graphical environment due to Wayland, you must access the Pi (I use SSH) and run sudo raspi-config. Go to Advanded Options > Wayland and switch to X11. Restart and you’re done.

That's all! Enjoy your VGA monitor with our beloved Raspberry Pi. I'll try the PCem (Thanks to PiKISS, of course 😉) emulator with MS-DOS or even Windows 98SE. Back to the 90s! I'm so excited! 😍

The best part that you are reading my blog is that I don't need to convince you with tons of resources like a dirty trickster to follow me. The resources I share with you are the best roadmaps for programming languages I found, now in 2024. Those are my personal preferences, and here are not all the language programming, only the ones I'm interested in according to my career, but I'm sure you will find them useful.

Laravel

If you like Laravel, you probably follow Povilas Korop, the creator of Laravel Daily. He has a great roadmap for Laravel and is very updated.

Link: laraveldaily.com/roadmap-learning-path

PHP

For PHP, I recommend the roadmap from PHP The RightWrong Way. It's a very complete guide for beginners and advanced users. You have a lot of resources and tutorials to start with PHP, from the basics to the advanced.

Link: phpthewrongway.com | OK, here you have the link to phptherightway.com too.

Front-End

I'm not like front-end, but as a freelance, I need to know the basics. I chose the roadmap from geeksforgeeks because It's very complete and updated. Check the tutorials and resources they provide (very useful, but ssh!... Don't tell anyone).

They have a MERN roadmap too, but I'm not a big fan of that stack. Maybe because I haven't used it yet. Do you recommend it?

Link: geeksforgeeks.org/frontend-developer-roadmap

Open Source Guides

If you are interested in contributing to open-source projects, you should check the next guides. They have a lot of resources and guides: Starting an open source project, contributing, licensing, best practices, and more.

Coded with love by GitHub and friends.

Link: opensource.guide

Developer roadmaps

If you are a developer, you should check the roadmap from Kamran Ahmeds. It's a very complete guide for people like you. From role to basic & advanced skill.

Link: roadmap.sh

I will leave you with another great resource called Exercism: A platform that provides coding exercises for different programming languages. Practice your skills and learn new languages.

Link: exercism.org

DSA

Too many devs always recommend learning Data Structures and Algorithms with the Princeton University courses (Part I, Part II). I'm not a big fan of that course and they are a bit boring.

If you are interested in this topic, you really should check the roadmap from Techie Delight. They have a lot of resources and tutorials with practical examples.

Final thoughts

Being a developer or starting a new career in programming is a challenge. Sometimes you can feel overwhelmed, but with the right resources, you can achieve your goals.

I forgot to mention If you are a complete newbie, you should check the CS50’s Introduction to Computer Science from Harvard University. It's a great course to start with the right foot.

I'm sure you will find this post useful. 😄

I have a problem with the software on my OS, maybe It's a disease, I don't know. The reason:

I try not to have many of them, but the apps I have installed need the latest updates. How do I get it? With some apps that help me on that mission. Do you want to know which ones? Keep reading!

Latest

Latest is a free and open-source app that checks if all your apps are up to date. It's a simple app that shows you a list of all your installed apps and the latest version available.

You can update them with a single click or one by one. It supports apps downloaded from the Mac App Store and apps that use Sparkle for updates, which covers most of the apps on the market.

If the app is not supported, you can open the app through Latest and check for updates manually.

Link: github.com > Latest

Cork

It's a fast GUI for Homebrew apps!

In the past, I used to update my apps with the terminal, but with Cork, I can do it with a single click (even when I love the Terminal).

It's a paid app, but you have the chance to compile and use it for free. It has many other features to handle visually your Homebrew apps: search, fix, install, uninstall,...

It just works & It's a great tool to keep your apps updated. Dot.

Link: github.com > Cork

Python cleanup script for macOS

mac-cleanup-py is a powerful cleanup script for macOS. It helps you in the next tasks: Empty Trash, delete unnecessary logs & files and clear cache from OS or some apps. You can enable specific apps to clean up, like Xcode or Android Studio. It has a very useful dry mode to see what it will do before running it.

Link: github.com > mac-cleanup-py

Custom function

So I think this is something all developers should have in their .*rc file: A simple function that checks if there are any updates available for the installed apps. For example, I use this function in my .zshrc file:

upgradeALL() {
    if [[ -f /usr/local/bin/composer ]]; then
        composer self-update
        composer global update
    fi

    softwareupdate --all --install --force
    brew outdated && brew update && brew upgrade && brew cleanup
    ## Add yours here!
    mac-cleanup
}

Conclusion

Now you have no excuse to keep your macOS updated. Of course, you can still use manual methods, but with these apps, you can have more control over the process in less time. Do you use any other app to achieve that? Let me know! 😃

This is the kind of article nobody reads, but everybody want to try. It's a simple trick to add an icon to a directory on macOS using a line command app called folderify. Instructions inside the article!...

To install, use brew:

brew install folderify

Then, to add an icon to a directory, just use the following command:

folderify mask.png /path/to/folder

For example, I've used this PNG image for the directory where I have all my source code:

Then I run:

folderify source_code.png $HOME/Documents/sc

Et voi là! I have a nice icon for that directory. ❤️

I own a license of Adguard on macOS and I'm happy with it. It blocks ads on the $potify desktop client, but I don't know what's wrong lately: It doesn't work anymore. So I found a better approach to block ads on $potify. It's a simple solution that works on both Linux and macOS.

TLD;DR: Run on your terminal:

bash <(curl -sSL https://spotx-official.github.io/run.sh)

Mmm, I don't trust you, Jose. What does it do?.

Good! Don't trust anyone. Here is the link to the repository:

https://github.com/SpotX-Official/SpotX-Bash

Sayonara,... Siri!

Here we have an interesting module for all AI enthusiasts!

The AI Hailo-8L M.2 is a HAT+ using PCI3 3.0 for AI accelerator module that delivers unprecedented performance. It is designed to accelerate AI workloads at the edge, enabling developers to deploy AI applications on Raspberry Pi with minimal latency and power consumption. It can gets an inference of 13 TOPS (Tera Operations Per Second). Their price is around $70.

You can use it for a wide range of applications, including:

• Image and video processing.
• Object detection
• Natural language processing.
• Neural network inference. ...

For more information, check the documentation here.

Where to buy?

You can buy the Kit from the following stores:

UK

• The Pi Hut £54.75 (excl. VAT)
• Pimoroni £65.70 (excl. VAT)

USA

• PiShop $85 (excl. VAT)
• Vilros $70 (excl. VAT)
• CanaKit $70 or with case, fan and heat sink $99.95 (excl. VAT)
• Sparkfun $70 (excl. VAT)

Spain

• The only place I found (anticipated, but sell at Jun, 14) is for Kubii.com 78,60 € (VAT included) and tiendatec.es 78,95 € (VAT included)

Wordwide

• Elector

Check the official Raspberry Pi site for more information and links to other stores.

I'm moving from my attic to the basement, and I needed to connect my Mac to the router, because the WiFi connection is terrible. I have a USB Ethernet device that I used with a miniPC, but it was not recognized by my macOS. I found a way to install it, and I want to share it with you.

Introduction

So, If you have a USB Ethernet device that is not recognized by macOS, you can try the following steps to install it. At least, it worked for me, and I hope it works for you, too. 😉

Steps

1. Open the Terminal and connect the USB Ethernet device to the Mac.
2. Run the following command to list the network interfaces:

networksetup -listallnetworkservices

3. Identify the new network interface that appears after connecting the USB Ethernet device. It should have a name like "USB Ethernet" or similar.

Now you have some information to get the driver for the device. You can search for the manufacturer's website or use any search engine to find the driver. In my case, It was ASIX AX88179 chipset, so I downloaded the driver from the official website. Another way is to search by product_id or vendor_id.

I only needed to install the driver, restart a couple of time, and the USB Ethernet device was recognized by macOS. I passed from 150 MB/s using WiFi to ~600 MB/s. Not bad!

Video showing the speed downloading RPi OS image from the Internet using Ethernet.

I must confess I'm not a very big fan of all products related with Jetbrains. All because its ecosystem is based on Java, and as a senior developer, we all hate Java. 🤣

Jokes aside, everybody is talking about Kotlin Multiplatform, so I decided to give it a try. This is a brief overview of the steps I followed to get started on macOS using Compose Multiplatform to build multiplatform apps. Is it worth it? Let's find out.

I'm going to tell you a story.

One day, at my grandmother’s house, my father brought a device that was connected to the TV. It was a ZX Spectrum 48k. After plugging it in and watching them load the cassette tapes (with a sound that was a little weird) and playing on the TV, I fell in love with this new machine. I had already seen an Atari with the Pong, but this was another level.

What I didn’t expect was that my father would start typing some letters and numbers that came in the instruction manual, and a few hours later, a spaceship would appear shooting enemies coming down the screen... That completely changed my world. I no longer wanted to be an astronaut, I wanted to be a video game developer!.

Movies like Tron and War Games didn’t help either. The point is, I’ve always had a concern about making video games, and I’ve done some games on MSX with BASIC and PC (DIV!) platform.

When I started growing up, the world of programming took me on other paths. I still have that thorn in my side, and a few months ago, I found out about all the excitement with Unity, and I thought again about an engine that caught my attention since it was released. I even did a talk in my hometown for a developer community. That engine is called Godot Engine, and today I want to talk about it if you don't know it and,... Who knows if I fulfill my dream of creating my own game!

What is Godot Engine?

Godot is a free and open source video game engine. It was created by Juan Linietsky and Ariel Manzur in 2007, and was released to the public in 2014. Today, it is maintained thanks to community donations and the support of some companies. The first thing that stands out is that to start working with it, you only need to download a file of a few megabytes (114 mb compared to the almost 16 GB of Unity!), and you can start to give it a go.

Pros

• Free: There are no licenses or royalties, one of the reasons why many developers are switching to Godot.
• Open source: You can modify the source code and make Pull Requests so that we can all benefit.
• Cross-platform: You can create your games on Windows, Linux and/or macOS. Then the project can also be exported to Android, iOS, HTML5 and consoles such as Playstation, Xbox and Nintendo Switch. By the way, it supports XR (VR) and ARM processors.
• Programming language: You can program in GDScript, a programming language similar to Python, or in C#/C++ among others (Have I seen Rust out there?).
• Community: Very active community, Discord and forums where you can resolve your questions.
• Assets Library: You don’t have to start from scratch. Visit the library where you can find assets visuals, sounds, music. **But remember! **: The assets are there to help you: don’t abuse them. Best of all, there are also tools that allow you to add functionality to Godot.

Cons

• Learning curve: Godot has a somewhat steep learning curve, especially if you do not have previous programming experience.
• Documentation: The documentation of Godot is not as extensive as that of other game engines, although the community is very active, especially after the bad decisions of Unity a year ago.
• Community: As I mentioned, the community is not as big as Unity or Unreal Engine, although it is growing more and more (+info).
• Assets: Although there is a library of assets as I have already mentioned, it is not as abundant as in the engines of competition.

How to start programming in Godot?

To start programming in Godot, the first thing you need to do is download the program from the official website.

Once downloaded, install it on your computer and open it. You will see that the editor is very intuitive and with many options. Although it can be overwhelming so many choices, don’t despair, everything has its function. You can start creating your first game from scratch, import one that you have already made or look at the examples that you can also download from the project menu.

I recommend, if you have no experience, that you start with the tutorials that are in the official website. You can also search for tutorials in YouTube or blogs. I leave you some links at the end of the post.

Tips

• Start with something simple: Don’t try to make a very complex game from the start. As with any working tool, you have to get experience. Go slowly. I would start with a platform game. Try following a tutorial like this one from Youtuber @wye to recreate Super Mario World and then modify it to your liking.
• Try everything Godot can do for you: Godot has many features that can save you time and effort. Try as much as you can and learn to use its options. Start by testing the mechanics, nodes and scripts. Then go for the physics and animations before embarking on a game of your own.
• Patience: Making a game is tedious, difficult, time-consuming, and requires a lot of patience. Don’t despair if it doesn’t come out right away. Try, fail, learn and try again. Set small goals and see them accomplished little by little.
• Learn from the community: Youtube, Discord, forums,... The Godot community is very active and can help you resolve your questions. Don’t be afraid to ask if you don’t understand something. Learn from others by reading code and understand what you intend to do, surely someone has solved the problem you are having with your game before you.

Final words

I just wanted to share with you my adoration for Godot Engine, and encourage you to try it if you have ever felt like me, and you have a desire to create video games. Do not pretend to get rich either or base your careers on it (for now). You do not need to have previous programming knowledge (although it helps). You can always start with tutorials and gradually go forward. If you want to create a game, tell me, I’d love to see it. 😉

Resources

Youtube

• Brackeys > How to make a Video Game - Godot Beginner Tutorial

• Leedeo Studio > Playlists

• GDQuest > Playlists

• Bastiaan Olij > Playlists

• DevWorm > Playlists

• Marcolm Nixon > Playlists

• LegionGames > Playlists

• MrElipteach > 10+2 AWESOME ADDONS for GODOT 4

• MrElipteach > Playlists

• Gamefromscratch > Playlists

• Coding Quests > Playlists

• Heartbeast > Playlists

• Lukky > All 219 Godot Nodes Explained In 42 Minutes

• StayAtHomeDev > Do THIS Before You Publish Your Godot Game

XR (VR)

• Muddy Wolf > Setting up the XR Origin - Build a VR Game in Godot List

• Boon Makes Games > Setting up XR/VR on Godot 4 | First Impressions, Passthrough, Hand tracking

• Blekoh > Making my Indie VR Game

Documentation, resources and blogs

• gdquest.com > Godot tutorials

• docs.godotengine.org > XR

• Godot Shaders

Finally, we reach the last principle of the SOLID series. The Dependency Inversion Principle is the most complex of all, but I'll try to explain it in a simple way.

I remember being asked about this principle in a recent job interview and I did not know what to say. Many times you know what it is by concept, but explaining it with an example is hard. If it happens to you, the best thing to do is to be honest and say so. It's okay and the interviewer will appreciate it.

Let's review all the principles we have seen:

• Single Responsibility Principle: A class should have only one reason to change.
• Open/Closed Principle: A class should be open for extension but closed for modification.
• Liskov Substitution Principle: You should be able to use any subclass in place of its parent class.
• Interface Segregation Principle: A class should not be forced to implement an interface it doesn't use.
• Dependency Inversion Principle: High-level modules should not depend on low-level modules. Both should depend on abstractions.

The Dependency Inversion Principle states that high-level modules should not depend on low-level modules. Both should depend on abstractions. Also, abstractions should not depend on details. Details should depend on abstractions. A lot of words, I know, but we'll look at it right now. Besides, I think this principle is the one that will help you the most in the long run.

Let's see some examples to better understand it:

// Bad
class MySQLConnection {
    public function connect() {
        return "Database connection";
    }
}

class PasswordReminder {
    private $dbConnection;

    public function __construct(MySQLConnection $dbConnection) {
        $this->dbConnection = $dbConnection;
    }
}

In this example, the PasswordReminder class depends on the MySQLConnection class. If you want to change the database connection to another type, you will have to modify the PasswordReminder class. This violates the Dependency Inversion Principle.

To solve this, you can use an interface:

interface DBConnectionInterface {
    public function connect();
}

# The MySQLConnection class implements this interface, providing its own implementation of the connect() method.
class MySQLConnection implements DBConnectionInterface {
    public function connect() {
        return "Database connection";
    }
}

class PasswordReminder {
    private $dbConnection;

    public function __construct(DBConnectionInterface $dbConnection) {
        $this->dbConnection = $dbConnection;
    }
}

Now, the PasswordReminder class depends on the DBConnectionInterface interface, not on the MySQLConnection class. If you want to change the database connection, you only need to create a new class that implements the DBConnectionInterface interface. This makes PasswordReminder more flexible and less coupled to a specific database connection implementation.

Do you not find it easy? Let's see another example:

interface StorageInterface {
    public function save($data);
}

class FileStorage implements StorageInterface {
    public function save($data) {
        // Save data to a file
    }
}

class DatabaseStorage implements StorageInterface {
    public function save($data) {
        // Save data to a database
    }
}

class UserController {
    private $storage;

    public function __construct(StorageInterface $storage) {
        $this->storage = $storage;
    }

    public function store($data) {
        $this->storage->save($data);
    }
}

$fileStorage = new FileStorage();
$userController = new UserController($fileStorage);
$userController->store("Some data");

In this example, the UserController class depends on the StorageInterface interface, not on the FileStorage or DatabaseStorage classes. This allows you to easily change the storage type without having to modify the UserController class.

We also note that UserController does not know how information is stored (details), it only knows that it is stored. The DatabaseStorage and FileStorage classes are the details and depend on the StorageInterface abstraction.

I hope you have enjoyed the last article about SOLID principles. In the future, I plan to investigate other design patterns.

Stay tuned! 😄

We are almost ending the series of articles about the SOLID principles. Here you have a brief explanation of each principle to review them:

• Single Responsibility Principle: A class should have only one reason to change.
• Open/Closed Principle: A class should be open for extension but closed for modification.
• Liskov Substitution Principle: You should be able to use any subclass in place of its parent class.
• Interface Segregation Principle: A class should not be forced to implement an interface it doesn't use.
• Dependency Inversion Principle: High-level modules should not depend on low-level modules. Both should depend on abstractions.

Today we are going to focus on the Interface Segregation Principle. It's very easy to understand, I promise. ❤️

This principle states that a class should never be forced to implement an interface that it doesn't use. If you implement an interface in a class, but only utilize a few of its methods, It indicates that you are violating this principle. An Example:

// Bad
interface Bird {
    public function fly();
    public function swim();
}

class Eagle implements Bird {
    public function fly() {
        return "I can fly";
    }
    public function swim() { <- Forced to implement a method that it does not need
        return "I can't swim";
    }
}

class Penguin implements Bird {
    public function fly() { <- Forced to implement a method that it does not need
        return "I can't fly";
    }
    public function swim() {
        return "I can swim";
    }
}

In this example, the Bird interface has two methods: fly and swim.

The Eagle and the Penguin classes implements both methods, but the Penguin class only should implements the swim method (Have you ever seen a penguin flying?), and Eagle should implement the fly method. This violates the Interface Segregation Principle.

An example with the correct way to implement the Interface Segregation Principle:

// Good
interface Bird {
    public function fly();
}

interface Swimmer {
    public function swim();
}

class Eagle implements Bird {
    public function fly() {
        return "I can fly";
    }
}

class Penguin implements Swimmer {
    public function swim() {
        return "I can swim";
    }
}

Now we have two interfaces: Bird and Swimmer. The Eagle class implements the Bird interface, and the Penguin class implements the Swimmer interface. This way, we are following the principle we are discussing. Easy, right?. 😄

I hope you have enjoyed the article today. If you have any questions or suggestions, in the meantime I add comments to the blog, you can send me an email.

See you in the next article!.

I like to use Terminal for everything (I'm an old school man). Check how I download the latest version of the Raspberry Pi OS for aarch64 (It's what I use), with the next command:

curl -s https://downloads.raspberrypi.org/operating-systems-categories.json | jq -r '.[0].images[0].urlHttp' | xargs axel -n 4 -k

As you can see, I'm using curl, jq to read the json file & axel as a download manager, because is the fastest method, but you can change it with its arguments.

Today, let's focus on the Open/Closed Principle.

First of all, here you have the four principles of SOLID:

• Single Responsibility Principle: A class should have only one reason to change.
• Open/Closed Principle: A class should be open for extension but closed for modification.
• Liskov Substitution Principle: You should be able to use any subclass in place of its parent class.
• Interface Segregation Principle: A class should not be forced to implement an interface it doesn't use.
• Dependency Inversion Principle: High-level modules should not depend on low-level modules. Both should depend on abstractions.

The Open/Closed principle states that "software entities (classes, modules, functions, etc.) must be open for extension, but closed for modification". So, once a software entity is developed and tested, it should be possible to extend its behavior without having to modify its source code.

Look the following code:

class Rectangle {
  public $width;
  public $height;

  public function __construct($width, $height) {
    $this->width = $width;
    $this->height = $height;
  }
}

class Circle {
  public $radius;

  public function __construct($radius) {
    $this->radius = $radius;
  }
}

class AreaCalculator {
  public function calculate($shapes) {
    $area = [];
    foreach ($shapes as $shape) {
      if ($shape instanceof Rectangle) {
        $area[] = $shape->width * $shape->height;
      } elseif ($shape instanceof Circle) {
        $area[] = $shape->radius * $shape->radius * pi();
      }
    }

    return array_sum($area);
  }
}

In this example, if you wanted to add a new form, you would have to modify the AreaCalculator class and add a new condition in the calculatemethod. In other words, Open/Closed principle said that you should be able to add new functionality to a class without modifying it.

The example above violates the Open/Closed principle.

A better way to do this would be to define a area method in each form and then call that method in AreaCalculator:

interface Shape {
  public function area();
}

class Rectangle implements Shape {
  public $width;
  public $height;

  public function __construct($width, $height) {
    $this->width = $width;
    $this->height = $height;
  }

  public function area() {
    return $this->width * $this->height;
  }
}

class Circle implements Shape {
  public $radius;

  public function __construct($radius) {
    $this->radius = $radius;
  }

  public function area() {
    return $this->radius * $this->radius * pi();
  }
}

class AreaCalculator {
  public function calculate($shapes) {
    $area = [];
    foreach ($shapes as $shape) {
      $area[] = $shape->area();
    }

    return array_sum($area);
  }
}

Now, if you wanted to add a new form, you would just have to create a new class that implements the Shape interface and defines the area method. The AreaCalculator class would not have to be modified to accommodate the new form. Therefore, it would comply with the Open/Closed principle.

In the noble art of coding, you should remember the SOLID principles always. Sometimes, I forget some of them, so here is a brief explanation of each principle:

• Single Responsibility Principle: A class should have only one reason to change.
• Open/Closed Principle: A class should be open for extension but closed for modification.
• Liskov Substitution Principle: You should be able to use any subclass in place of its parent class.
• Interface Segregation Principle: A class should not be forced to implement an interface it doesn't use.
• Dependency Inversion Principle: High-level modules should not depend on low-level modules. Both should depend on abstractions.

Today we are going to focus on the Liskov Substitution Principle.

This principle states that "functions that use pointers or references to base classes must be able to use objects of a derived class without knowing it".

In other words, derived classes must be completely substitutable for their base classes. If a derived class cannot be substituted for a base class, then the class hierarchy is not well designed and violates Liskov's substitution principle.

Here you have an example on PHP about it:

// Bad

class Bird {
    public function fly() {
        return "I can fly";
    }
}

class Penguin extends Bird {
    public function fly() {
        return "I can't fly";
    }
}

function letItFly(Bird $bird) {
    return $bird->fly();
}

echo letItFly(new Bird()); // "I can fly"
echo letItFly(new Penguin()); // "I can't fly"

In this example, Penguin is a subclass of Bird. However, not all birds can fly, so when we try to make a Penguin fly, we get an unexpected result. This violates Liskov's substitution principle.

A better way to do this would be to have a Bird base class and a Flyable interface that only implement birds that can fly:

class Bird {
}

interface Flyable {
  public function fly();
}

class Sparrow extends Bird implements Flyable {
  public function fly() {
    return "I can fly";
  }
}

class Penguin extends Bird {
}

function letItFly(Flyable $bird) {
  return $bird->fly();
}

echo letItFly(new Sparrow()); // "I can fly"

In this example, if we try to fly a Penguin, we will get a compile-time error, because Penguin does not implement the Flyable interface.

Another example:

// Bad

class Animal {
  public function eat() {
    return "I can eat";
  }
}

class Lion extends Animal {
  public function eat() {
    return "I can eat meat";
  }
}

class Rabbit extends Animal {
  public function eat() {
    return "I can eat vegetables";
  }
}

class Plant extends Animal {
  public function eat() {
    throw new Exception("Plants do not eat");
  }
}

function feed(Animal $animal) {
  return $animal->eat();
}

echo feed(new Lion()); // "I can eat meat"
echo feed(new Rabbit()); // "I can eat vegetables"
echo feed(new Plant()); // Exception: Plants do not eat

// Good

class LivingEntity {
}

interface Eatable {
  public function eat();
}

class Lion extends LivingEntity implements Eatable {
  public function eat() {
    return "I can eat meat";
  }
}

class Rabbit extends LivingEntity implements Eatable {
  public function eat() {
    return "I can eat vegetables";
  }
}

class Plant extends LivingEntity {
}

function feed(Eatable $entity) {
  return $entity->eat();
}

echo feed(new Lion()); // "I can eat meat"
echo feed(new Rabbit()); // "I can eat vegetables"

I hope we understood it. See you in the next principle!.

In the noble art of coding, you should remember the SOLID principles always. Here is a brief explanation of each principle:

• Single Responsibility Principle: A class should have only one reason to change.
• Open/Closed Principle: A class should be open for extension but closed for modification.
• Liskov Substitution Principle: You should be able to use any subclass in place of its parent class.
• Interface Segregation Principle: A class should not be forced to implement an interface it doesn't use.
• Dependency Inversion Principle: High-level modules should not depend on low-level modules. Both should depend on abstractions.

Today we are going to focus on the Single Responsibility Principle.

Here you have an example on PHP about it:

class Order
{
    private $items = [];

    public function addItem($item)
    {
        $this->items[] = $item;
    }

    public function calculateTotal()
    {
        $total = 0;
        foreach ($this->items as $item) {
            $total += $item->getPrice();
        }
        return $total;
    }
}

class Item
{
    private $name;
    private $price;

    public function __construct($name, $price)
    {
        $this->name = $name;
        $this->price = $price;
    }

    public function getPrice()
    {
        return $this->price;
    }
}

$item1 = new Item('Taco', 2.99);
$item2 = new Item('Burrito', 4.99);

$order = new Order();
$order->addItem($item1);
$order->addItem($item2);

$total = $order->calculateTotal();
echo "Total: $" . $total; // Total: $7.98

The Single Responsibility Principle (SRP) states that a class must have only one reason to change. This means that a class must have only one responsibility and must have no more than one reason to be modified.

In the code above, we can identify two classes: Order and Item. These classes follow the principle of single responsibility, as each has a single responsibility and has no more than one reason to change.

The Order class is responsible for representing an order and performing operations related to it, such as adding elements to the order and calculating the total, and handle the logic of the order.

The Item class represents an item and provides methods for obtaining its price. It has the responsibility to represent an article and provide information about it.

As we can see, each class has a unique responsibility and there is no mix of features in any of them.

This is beneficial because if in the future we need to make changes in the logic of the order, we just need to modify the Order class. Similarly, if we need to make changes in the representation or behavior of an article, we just need to modify the Item class. This facilitates code maintenance and reduces the risk of errors when making changes.

I hope this example helps you to understand the principle of single responsibility and how to apply it in your code.

Today I was asked this question in a job interview, and I found it to be a very simple way to explain dependency injection. Here's the explanation I gave, a bit more detailed (I'm sure it blew my interviewer's mind):

Imagine you're preparing a turkey for a special dinner. The turkey needs to be stuffed to have a delicious flavor. You could put the stuffing directly inside the turkey, but that would limit your options. If you wanted to change the stuffing, you would have to take out the entire turkey and start over.

Instead, you decide to use a bag for the stuffing. You put the stuffing in the bag and then put the bag inside the turkey. Now, if you ever want to change the stuffing, you can simply take out the bag and put in a new one with a different stuffing. You don't need to dismantle the whole turkey.

In programming, "dependency injection" is like using the bag for the stuffing. Instead of putting the dependencies (the stuffing) directly in your code (the turkey), you put them in something that can be easily changed (the bag). This makes your code more flexible and easier to change or reuse in the future.

All prompts are extracted from the app Fixkey. It's an app that uses AI to help you write better. It provides prompts to improve your writing, fix grammar,... Available for macOS, I use it a lot, but It's a trial version, and unfortunately, I don't have the money to subscribe to the app right now. If you can afford it, I recommend it.

If you go to the settings, you can check the prompts used by the app. I think these prompts are very interesting for any project. Even I am looking to make a similar app using Python. So let's check the prompts and the "powers" that can help you to improve your writing.

Fix grammar

Revise the given text to correct any grammatical errors. Focus on improving sentence structure, punctuation, verb tense consistency, and word usage. Ensure the text adheres to standard grammar rules of the language this text is written in, enhancing readability and clarity. When the sentence has a bullet point at the beginning, don't remove the bullet point, otherwise answer with raw text. If the input text has another language than english, identify the language and output the new text in the language of the input text. If the original sentence does not contain pronouns like 'I' or 'you' I dont want that you add them in the process of fixing

Revise the given text to correct any grammatical errors. Focus on improving sentence structure, punctuation, verb tense consistency, and word usage. Ensure the text adheres to standard grammar rules of the language this text is written in, enhancing readability and clarity. When the sentence has a bullet point at the beginning, don't remove the bullet point, otherwise answer with raw text. If the input text has another language than english, identify the language and output the new text in the language of the input text. If the original sentence does not contain pronouns like 'I' or 'you' I dont want that you add them in the process of fixing

Improve writing

Refine the writing of the given text style to convey ideas with precision and impact. Pay attention to the appropriate tone for the intended audience, whether it be formal, informal, persuasive, or informative. Focus on clarity by organizing thoughts logically, avoiding ambiguity, and providing clear transitions between ideas. Strive for conciseness by eliminating unnecessary wordiness and refining sentences for brevity without sacrificing clarity. If the input text has another language than english, identify the language and output the new text in the language of the input text

Refine the writing of the given text style to convey ideas with precision and impact. Pay attention to the appropriate tone for the intended audience, whether it be formal, informal, persuasive, or informative. Focus on clarity by organizing thoughts logically, avoiding ambiguity, and providing clear transitions between ideas. Strive for conciseness by eliminating unnecessary wordiness and refining sentences for brevity without sacrificing clarity. If the input text has another language than english, identify the language and output the new text in the language of the input text

Convert To bullet points

Transform the given content into bullet points. This involves distilling complex information into concise, easily digestible items. Focus on extracting key ideas and essential details. Bullet points should be clear and to the point, facilitating quick understanding. Ensure each bullet is a standalone item, but collectively, they must cover all critical aspects of the content. Ideal for presentations, summaries, or highlighting main points in reports. Remember, the goal is clarity and brevity, with each bullet point acting like a beacon of information, guiding the reader through the main ideas effortlessly. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Transform the given content into bullet points. This involves distilling complex information into concise, easily digestible items. Focus on extracting key ideas and essential details. Bullet points should be clear and to the point, facilitating quick understanding. Ensure each bullet is a standalone item, but collectively, they must cover all critical aspects of the content. Ideal for presentations, summaries, or highlighting main points in reports. Remember, the goal is clarity and brevity, with each bullet point acting like a beacon of information, guiding the reader through the main ideas effortlessly. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Summarize

Can you provide a comprehensive summary of the given text? The summary should cover all the key points and main ideas presented in the original text, while also condensing the information into a concise and easy-to-understand format. Please ensure that the summary includes relevant details and examples that support the main ideas, while avoiding any unnecessary information or repetition. The length of the summary should be appropriate for the length and complexity of the original text, providing a clear and accurate overview without omitting any important information. Do not reference the text answer with summary straight away. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Can you provide a comprehensive summary of the given text? The summary should cover all the key points and main ideas presented in the original text, while also condensing the information into a concise and easy-to-understand format. Please ensure that the summary includes relevant details and examples that support the main ideas, while avoiding any unnecessary information or repetition. The length of the summary should be appropriate for the length and complexity of the original text, providing a clear and accurate overview without omitting any important information. Do not reference the text answer with summary straight away. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Explain this

Explain this concept intuitevely.

Explain this concept intuitevely.

Make shorter

Condense the provided text into a shorter version. Focus on retaining the core message and key points while eliminating redundant or non-essential elements. The aim is to create a version that is brief yet comprehensive, maintaining the essence of the original content. Ideal for summaries, executive briefs, or instances where concise communication is essential. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Condense the provided text into a shorter version. Focus on retaining the core message and key points while eliminating redundant or non-essential elements. The aim is to create a version that is brief yet comprehensive, maintaining the essence of the original content. Ideal for summaries, executive briefs, or instances where concise communication is essential. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Translate to English

Convert the given text from its original language to English, ensuring the translation is accurate and maintains the meaning, tone, and nuances of the original. Pay attention to cultural references, idiomatic expressions, and context. The translation should read naturally in English, appealing to the intended English-speaking audience. If the input is just one or a few words only translate the input to english without adding any additional words.

Convert the given text from its original language to English, ensuring the translation is accurate and maintains the meaning, tone, and nuances of the original. Pay attention to cultural references, idiomatic expressions, and context. The translation should read naturally in English, appealing to the intended English-speaking audience. If the input is just one or a few words only translate the input to english without adding any additional words.

Change to markdown

Convert the given text into Markdown format. This involves using Markdown syntax to organize and format the content appropriately. Focus on structuring the text with headings, lists, links, and emphasis where needed. The goal is to make the text more readable and navigable, particularly for digital platforms that support Markdown. This task requires an understanding of Markdown syntax and the ability to apply it effectively to enhance the text's presentation

Convert the given text into Markdown format. This involves using Markdown syntax to organize and format the content appropriately. Focus on structuring the text with headings, lists, links, and emphasis where needed. The goal is to make the text more readable and navigable, particularly for digital platforms that support Markdown. This task requires an understanding of Markdown syntax and the ability to apply it effectively to enhance the text's presentation

Change to Casual

Rewrite the given text in a casual, conversational style. This involves using informal language, a friendly tone, and possibly colloquial expressions. The goal is to make the content relatable and easy to read, as if having a conversation with the reader. Ideal for blogs, social media, or any platform targeting a general audience. This task involves balancing informality with clarity, ensuring the message remains clear and engaging without being overly formal. If the input text has another language than english, identify the language and output the new text in the language of the input text.

Rewrite the given text in a casual, conversational style. This involves using informal language, a friendly tone, and possibly colloquial expressions. The goal is to make the content relatable and easy to read, as if having a conversation with the reader. Ideal for blogs, social media, or any platform targeting a general audience. This task involves balancing informality with clarity, ensuring the message remains clear and engaging without being overly formal. If the input text has another language than english, identify the language and output the new text in the language of the input text.

tuples and lists are two types of data incorporated in Python that are used to store collections of elements. Although they share some similarities, they also have key differences. Let’s look at them:

This is the second part of the series of articles about how has been the experience of migrating a blog made in PHP + MySQL, to a static one using Vuepress 2. Here I talk about the old code structure and the technology used. Let's go!

This is one of those things that I do every day, and the flow is very boring: Open Quicktime, cancel the box dialog, Go to File > File > New Movie Recording, and then select the device. I mainly use it to view the signal from a USB video capture device, which works much better than doing it via VNC, Remote Desktop, or similar. In addition, these types of capture devices are very cheap.

So today I'm going to show you how to open Quicktime and start streaming a device on macOS using the command line or making an Automator script.

DietPi, in its recent 9.1 release, introduces several exciting enhancements and bug fixes. Notably, it now provides support for the Raspberry Pi 5. Additionally, various dietpi-software options have been refined.

The new Raspberry Pi 5 images, based on the latest Bookworm kernel and firmware package set from Raspberry Pi Ltd, are available for testing. However, some features—such as changing screen resolution and camera module support—are not yet functional. DietPi’s primary focus remains on performance and a compact installation size, with extensive configuration tools that allow for more customization than usual. If the performance gains, reduced RAM usage, and faster boot times observed on the Raspberry Pi 4 persist, Die_tPi can provide a welcome boost to the Raspberry Pi 5 while also being energy-efficient.

Source: DietPi

Just a quick tip If you want to read a Medium article for free, cuz you don't have money to pay for a subscription or you don't want to create an account.

If you want to run a script for example, after apt update on Debian, you can use the apt hook system. This is useful if you want to perform some other action after the update. In my case, I need to run a script and re-install the Vulkan driver on Raspberry Pi, because apt update break it and the system can't open the Desktop environment.

Sometimes I think I'm the one who has problems with the NTFS/exFAT partition on macOS. I have to unmount and clean it, because exFAT is the file system I use on a Raspberry Pi acting as NAS using the great DietPi OS.

It's been 3 years since my last post here. I have been busy with my work and other projects. The new focus I want to give to the blog is going to be a bit different. Less Raspberry Pi (I will tell why later) and more technical.

I want to share with you a series of articles about how has been the experience of migrating a blog made in PHP + MySQL, to a static one using Vuepress 2.

On this image You will find the famous Commodore 64 emulator VICE.

When powering on the RPi there is an automatic login with the user c64 (password c64) and then the emulator is started.

There are some files already installed in the /home/c64/c64 folder, split by disk images, tape images and other.

Link: C64 Emulator

Games: Search .sid files

> wget --no-parent --recursive --level=1 --no-directories --user=login --password=pass https://myftpsite.com/

It's valid to ftp sites too.

I see my Google Docs' notes has nearly the same success (or even more) that this blog 😛

I updated and ordered the next sections: blogs, forums, Other blogs

It's in spanish, but links are mainly in english.

Link: G Docs

My wife has had a delicate operation in which nearly lost his life as she has suffered a brain stroke with 35 years old. Fortunately, thanks to a arteriography held in Virgen del Rocio Hospital (Seville, Spain), found three [aneurysms](https:// www.arteriasyvenas.org/index/aneurysms) and closed two. Hopefully in a couple of weeks we stared at home and we can continue to update the blog.

Thank you!

I like to put on my blog news that you can't find on the normal channels, mostly so that you do not see always the same boring news about GPIO, libraries and custom projects: P

I'd like to show you livarPi.

I'm back!

Probably the worst three weeks of my life, but everything is back to normal and my wife is recovering slowly.

This first post, I leave an updated link comparing these three distributions based on XBMC.

What is your favorite?

Link: goshawknest

Raspberry Control - Control Raspberry Pi with your Android Device.

Application Features:

• secure connection via SSH,

• easy control and monitoring GPIO,

• monitor and graph temperatures remotely using DS18B20,

• remote terminal emulator,

• remote process management,

• built-in MJPEG stream client,

• easy 1-wire and I2C bus management,

Raspberry Control soon available in Google Play (Android app) and Pi Store (Raspberry Pi app).

Note: Their author just told me that this app will be available in this weekend (Google Play) 😄

Our friends RaspiPC.es recommended me a blog by Javier Pardo Blasco quite interesting.

First Raspberry Pi's unboxing and the steps he took to make it operational.

The second is a home automation with the RasPi.

Welcome to this exciting world, Javier.

Link: Unboxing Raspberry PI

Link: Domotic with Rasberry PI

I just found a script to display the temperature under your Raspi terminal. If you are interested...

#!/bin/bash
# Script to show the temperature of the Raspberry Pi in terminal
# Values can be adjusted to show different color temperatures.
# By default:
#      40 degrees or less -> green (32)
#      Between 41 and 54 -> yellow (33)
#      Greater than or equal to 55 -> red (31)

mgrados='cat /sys/class/thermal/thermal_zone0/temp'
engrados='expr $mgrados / 1000'

if [ $engrados -le 40 ]; then
	echo -e "Temp CPU:\033[32m $engrados"
elif [ $engrados -gt 40 ] && [ $engrados -lt 55 ]; then
	echo -e "Temp CPU:\033[33m $engrados"
else
	echo -e "Temp CPU:\033[31m $engrados"
fi

Those who live in the Spectrum's era, usually dream with cover girls from the great artist Alfonso Azpiri.

I found a 2013 calendar with the sexiest girls from Spectrum. Enjoy! 😉

Link: Calendar

I missed the MagPi translated into Spanish. They are looking for translators, in case anyone is encouraged.

I wish you lucky and much encouragement.

Link: The MagPi

To save and compress, the command is as follows (replace xxx with the ID of your disc):

dd if=/dev/xxx conv=sync,noerror bs=4m | gzip -c > xxx.img.gz

To decompress and restore, the command is as follows (replace xxx with the ID of your disc):

gunzip -c xxx.img.gz | dd of=/dev/xxx conv=sync,noerror bs=4m

For other operating system than OSX, use capital M.

Source: pihomeserver.wordpress.com

He has posted a Top 10 Raspberry Pi Blogs. Don't miss it!

Link: jeremymorgan.com

On my iMac I have a partition with Windows 8 (damn).

Basically I use it to... nothing, maybe play sometimes, and It's difficult to get some updated drivers to test a game or cool benchmarks... until now.

NOTE: Also applies to Windows 7 or 8 computers, whether desktop or laptop especially, who are facing more problems.

I have a few days between work extreme fighting with MySQL and leisure spending PAL to NTSC audio from Mac to put in a video. Let's see if I can tinker with Raspi, as I have prepared several tutorials that I hope you like them.

I leave you with an article of those where we like to compare these three monsters of the digital age, they are the jewel of microcontrollers.

Link: makezine blog

It seems that the Raspberry Pi had its moment of glory, and is already looking for another PCB to do more for the same price. Beaglebone has fit some features of your card, and now sell for $45. Is it worth it? Let's see its features...

But anyway, my fault. Not much value I have found, so I leave you with a few steps to be able to run Adobe Flash Player on the Raspberry Pi, which is that I like it.

Link: mrpiworld.wordpress.com

Atention! I just read and I don't believe it. Bodhi Linux, an Ubuntu based distro, has been ported to Raspberry Pi.

I have a gift for us!

This is the reason because I have been busy these days. I got the idea of having a cheat sheet with information that is always good to have on hand. And to make it look pretty and practical, I present to all the SINGLE NOTES ON A CUBE TO RASPBERRY PI... EL CUBOpuntes! (a.k.a. NOTESbox)

On this unfortunately named CUBOpuntes I have compiled some information you will have to consult securely.

But certainly not without faults, so if you see something wrong, a command that does not work, you need that package essential, just let me know. If you have another name for the baby, I'll be watching the comments.

The information gathered:

• Side 1: Logos, schema and GPIO.

• Side 2: Copy OS to SD.

• Side 3: Files you should know and its location.

• Side 4: Useful commands I.

• Side 5: Useful commands II.

• Side 6: Shortcuts keys in the terminal and Favorite apps.

Hope you all like it!

PS: I am not responsible if you stick your fingers with the glue or hurt yourself with the scissors because your lack of experience.

Link: NOTESbox PNG in English | NOTESbox PDF in English

Descarga: CUBOpuntes PNG in Spanish | CUBOpuntes PDF in Spanish

Well, at last Friday. This weekend we play with our Raspberry Pi. I give some ideas to cover news this week have been several blogs.

• PiParted v0.03

  Distribution from GParted LiveCD ISO dedicated as you all know to download and install distros from Raspberrypi.org (easy method). Size: 149 MB.

• Rpix86 has logo!

  Finally have this great DOS emulator logo. Patrick has been busy, but the MIDI synthesizer support continues to progress.

• PiMAME 0.6 Beta 5 - Now with PlayStation support!

  As you can seen in the video, everything seems to go quite well with the PSX1 emulator. In the next version will come with a distribution updater not have to be downloaded every time an image.

• New OpenELEC 3.0.1

  Frodo 12.1 Updated with corrections for our Raspi among others, several drivers and packages updated in the distro. Full list of changes here. Download here

• Starting with Arch Linux

  One of these days I will try this fantastic distro. Fran Carver has an article explaining the first contact he had with Arch Linux in Raspi.

Ever since my first PC 286 to the present days, I have been obsessed with optimization: an operating system, programming code, an application...

We are going to know how to optimize a little our Raspberry Pi.

New version of this distribution which now supports more emulators. From here we give Shea Silverman Congratulations on your marriage, because he has been married a few weeks ago.

Probably site Diverteka is one that has more hispanic fans. Its clean Wordpress theme and content so enriching is what motivates us every day to visit their website.

This essential reference will guide you through a series of exciting projects that will allow you to automate your very own home. With easy-to-follow, step-by-step examples, diagrams, and explanations you will not only find it incredibly productive but also highly engaging and informative.

What you will learn from this book:

• Install an operating system for your Raspberry Pi.

• Set up the Raspberry Pi and Arduino bridge shield.

• Learn how to work with electronic components to build small circuits.

• Develop applications that interact with your circuits.

• Use thermistors and photoresistors to monitor and control your surroundings.

• Control your own mains power with a relay shield and even connect a motor to your Raspberry Pi.

Purchase: Amazon

Today is one of those days that excites me. First, today Canonical released a new Ubuntu OS and with a new version I feel like a child to test it on my iMac. So today did not bother me, LOL.

Second because the tutorial that I found today is on diet Raspbian distribution for those who do not get into LXDE for anything, and we connected our Raspi Ethernet cable. These are simple steps, and you lose nothing to try the script that have element14 forum.

Link: Element14

First of all thanks for the welcome given to the NOTESbox (nobody has told me anything about the name, I guess you like). I never received so many hits so far, even with the RetroPie guide with which I took a week. It seems that you prefer manual labor, lol.

Well, I just found a very interesting article on a temperature-controlled room with the Expansion Board you can find in this Store.

Link translated into English: Electronica Ensaimada

On Friday April 12, 2013 will be the first meeting (presentation, order of material and introduction to management system) Rasperry workshops Pi 2013 local Student Branch (North Aulario).

These days I've been doing something that if all goes well, I will publish by the end of the week. Surely you all like. 😉

I wanted to give you the news that I have been in contact with Juande, one of the creators of the company raspipc.es, to reach an agreement with this blog.

Raspipc is a company with which I have worked, and I have only words of kindness by how quickly deliver their orders and seriousness when working here in Spain. If you're from here, would not hesitate to purchase products through its Store.

I am very happy and confident that we can soon make the odd contest for you all. What do you think?

Welcome!

Monday and I could not have touched the Raspi, but I have something going on... 😉

I link to a post that I found quite full. I dedicate it to my father, who sure likes.

Translated link: sistemasorp.es

This version contains the following fixes and improvements:

We have a new version of our favorite MS-DOS emulator.

I would like to say one thing to Patrick after the criticism he has had because some routines he have copied from Dosbox ...

rpix86 version 0.06 released!

This version contains the following fixes and improvements:

It's amazing how well they have mastered the touch system in the Ubuntu updated operating system that has to go out this month.

I believe that although I have always seen it as a waste of time, since the keyboard and mouse will always be much faster than touching the screen and staining it, are moving in a very positive way with this control system.

If they want to somehow revive repetitive features that are occurring in the operating systems and to copy each other, one will have to uncheck from the rest.

Ubuntu although criticized for decisions that are altering its operating system for better or worse are trying it at least, and I dare say better than Microsoft with their Windows 8.

Would you like to control your desktop with your fingers?

It is among us the new Ubuntu 13.04 from Canonical. I'll report ...

Download: Ubuntu Raring ringtail

Screenshot Tour: noobslab.com

Tweaks: Things/Tweaks to do after Install of Ubuntu 13.04 Raring Ringtail

A few days ago version 0.4 released, and would not comment if I get many positive changes in this emulator. If you want to know what new features brings...

Well, I have nothing prepared for this great event, but it deserves a few words.

Two months have passed since the blog started. There are still many things to do around here, and as you know I've been out a few weeks because of my wife.

Almost 100 post, visitors from USA, UK, Argentina, Chile, Germany, France, Mexico and particularly Spain.

First, let me thank the comments of encouragement that I have received, both on Twitter and in the blog. It seems silly, but I was excited about your comments on this difficult moments, and this makes a difference to me. Now you are part of my circle, as would said Google 😉

Now it is making some progress on the web (I hope I do not take another 10,000 visits). Most you come here to read news about Raspberry Pi, I know, and forgive me that sometimes post content that interests me. Let's see if I can separate content for anyone having to read any of the other topics that interest to me, both in the feeds and with the sections in the header.

Of course, any improvements or advice you may offer, are welcome. I also want that this blog to be a point of interest to help you spread your post or blog. Whenever you want to give visibility to your post, please send me your link, which I will publish it. Ditto if you have a store or business.

This post is dedicated to my wife who encouraged me to continue the blog, and my daughter, who can't stop dancing Mickey Mouse Club House and were it not for the 27" iMac, it would be impossible to devote time to blog .

And you, of course!. Hope to continue reading, the best is yet to come...

I have two applications on Mac to create a backup of your SD card (PiCloner) and another that is a graphical interface to copy the operating system from the .img file to SD (PiWriter).

Remember the right way to do the same as PiWriter in the Mac Terminal:

N is the drive of your SD card
$ diskutil list
$ sudo diskutil unmountDisk /dev/diskN
$ date +'Start: %H:%M:%S' && sudo dd if=myImage.img bs=1m of=/dev/rdiskN
$ diskutil eject /dev/diskN

Link: PiCloner

Link: PiWriter

What a coincidence!. I found online an article about Raspberry Pi of the British publication called Custom PC UK. Apparently is from May, 2013 (WTF!).

In this magazine we teach various tricks, apps and how to stream and record TV channels through our Raspberry Pi. It also teaches several distros to choose the ones you like.

PS: I encourage people to buy the magazine or subscribe to it better.

Subscription: Linux Format UK

I found a pretty curious post about home automation project that I want to show you. Nothing better than the words from the author about this project to know it:

I recently presented a project with the Raspberry Pi in college where I study Computer Science.

The goal was pretty generic and was used GPIO pin header that brings the Raspberry Pi and to control the I/O from a mobile device.

So for this project I thought of making a model of a home and simulate home automation.

Link: Mis experiencias con la Raspberry Pi

This weekend we have an important mission. No matter the emulator or the game, but the platform.

First, let me thank you for the great reception given to the RetroPie's guide that I published a few days ago. The visits have gone through the roof and now I have a daily average of 400 visits. For a blog devoted entirely to something as specific as the Raspberry Pi has a special merit. Anyway I don't understand how it is possible that Google Docs continues to have such popularity and every time I go to the doc I see an average of 10 users online: P

Now I want to write about an offer for Mac. You need to register and you get at your disposal a number of free applications, which otherwise would cost you a bunch of dollars (in this case an average of 130$). If you have a Mac, take advantage.

Link: MacUpdate

Carrots is like a service to connect mobile internet devices. Following these instructions will have a teddy-cyborg with Raspberry Pi's hearted that will delight the little kids.

The tip is to keep your profile in RAM. This uses the tmpfs filesystem.

Its website says the following about Kali:

From the creators of BackTrack comes Kali Linux, the most advanced and versatile penetration testing distribution ever created. BackTrack has grown far beyond its humble roots as a live CD and has now become a full-fledged operating system.

Would you like that I make a tutorial about their use?

Link: Download Kali

Cheatsheet: Kali Linux Cheat Sheet

Learn Raspberry Pi with Linux will tell you everything you need to know about the Raspberry Pi's GUI and command line so you can get started doing amazing things.

Sometimes I think the only thing that interests me from Raspi are emulators. I see Frogger in the Pi and the nostalgia come to me :_)

I show you an email sent to me about a Rasbberry meeting in Barcelona (Spain):

Greetings and congratulations because your document on Raspberry Pi, who are "newbies" like this shared and updated documentation. Also congratulations on your new blog, wish good luck. I pass a link of a "meeting" in Barcelona:

https://lanyrd.com/2013/raspberrypizza/

It will be a "geek stuff" but I found very interesting the term "Raspberry pizza", about Raspberry Pi brainstorm with the idea about sharing and enjoying the pizzas...

Greeting.

Marius

What leads people worse on Raspberry Pi is Flash support (an advance) and slow web browsers like Chromium.

I propose another one. It's based on WebKitGTK engine and start up in 1 second!.

Their author said about it:

We have patched a lot of bugs, removed that horrible text-mode rom selector, moved all options menus to graphic mode (except rapsbian ones).

Hope all you like as much as we enjoyed creating it.

Downloads: Torrent | Direct download

As discussed in Raspbmc's forum, a new firmware has been release and fix the pop sound before and after played media. Good news for all. Did anyone test it on Raspbian and want to comment?

Link: stmlabs.com

Probably the best distribution for enjoying a good media center with XBMC. At least with faster boot times.

A Raspberry Pi forum user put few days ago, a compiled binary of PCEngine emulator. Apparently everything runs perfectly, but no one has left a comment, so I'll put it here to see if anyone is encouraged to test it.

All the information on the second link.

Link: forum

Link: PCEngine/TurboGrafx-16 Emulator Mednafen Module

The previous post was my 100th post, and I see that every day is more difficult to find updated news about our Raspi. Many blogs have several days without updating, and perhaps means the Pi fever is down. Hopefully not.

We all tend to use either Raspbian or Arch Linux. Sometimes they do not bother to try other alternatives. Wrong.

PiBang is a good solid distribution now takes a version Server, all command-line based on Debian and access to their repos. Also you may be interested in their desktop version that uses OpenBox instead of LXDE, lighter.

Enlace: Imagen PiBang Server Ed.

Enlace: Raspbian Vs Raspbian

A blog reader of your favourite blog (this, of course) has done us the favor to all Spanish speakers to translate an article from Linux Format Magazine. Try to record and broadcast TV channels with a Raspberry Pi.

The ingredients: TDT-USB receiver, XBMC and the plugin TVheadend.

Link: blamarpa blog

It's available for Android a new version of this software to control various aspects of our Raspberry Pi. You need to install a software in your Raspi, but you will have available the following features:

How is the experience from the user?, Is it difficult to use?, Is it worth one Raspberry Pi?, How is that back to basics and manage our devices, often from a terminal?

All these questions and their answers on a post made ​​by Fernando Dotuel to Xataka website.

Link: Xataka

I just read a very interesting article from the plugin's creator Pelis a la carta. It explains how to install very easily Raspbmc distro and configure it to access their plugin. Do not miss it!.

Link: blog.tvalacarta.info

Link: sirlagz.net

A comment on my Google Docs has made me know this site, their shop and a very interesting tutorial about how to watch TV channels and TV sport with a plugin called rmtpGUI + modified.

Link: goshield blog

A blog reader called Hugo Ruiz, told me days ago we have a new distribution based on OpenELEC, but using the Plex app, which as many of you know, is an alternative with enough followers to XBMC.

It's still in beta, but it works pretty well. Supports AirPlay and AirTunes.

Link: RasPlex

I'm very excited to share with us this post 😄

I decided to make a tutorial a little longer than usual. Today we will test this distribution based on Raspbian and making accessible to anyone the world of emulators with a Raspberry Pi as I mentioned above. Let's Start!

NOTE: This review is based on SD-card image from 03/07/2013, but also is valid for the script you can find on GiHub.

This is an SD-card image with a ready-to-go installation of the RetroPie Setup Script. It needs an SD-card with at least 4 GB space.

If you want to know what systems are supported...

I have wanted to have a look at this great operating system. Perhaps preparing a post in Spanish, as I have not seen one and could be useful to someone. What do you think?

Meanwhile, I leave you with this one that I found very useful.

Link: element14 - Discovering RISC OS Pi