echo.hive (@hive

echo.hive

21.1K posts

echo.hive

@hive_echo

exploring the self and the AI… 🟣 Maximize yourself: patreon.com/collection/184… 🔴Consulting: echohive.ai/consulting

Joined July 2022

Pinned
echo.hive
@hive_echo
Apr 1
My longest running consulting client(2+ years) wanted to build an AI chatbot for his restaurant Today he's the Lead of GenAI R&D at Amsterdam University of Applied Sciences. Because @WonderWhyAI is relentlessly driven and curious, our monthly 1-on-1 sessions went deep: -
Fausto Albers
@WonderWhyAI
Jan 20
I studied to be a sociologist, became a restaurant owner, and then transitioned to AI research. I now lead GenAI R&D at AUAS Industrial Digital Twins Lab. What I have learned contradicts much of what people assume about AI and coding. Essay -> wonderwhy.ai
9.7K
echo.hive
@hive_echo
Oct 24, 2025
I built a biologically inspired spiking neural network from scratch and it learned with %5 accuracy to do addition :) There is no backpropagation, no artificial loss functions - just spikes, synapses, and dopamine-like reward signals. it uses STDP -> "Spike-Timing-Dependent
00:00
447K
echo.hive
@hive_echo
Apr 9, 2025
!!! BREAKING !!! Grok-3-mini is the first model that gets a full perfect score in my reasoning test! Congrats to @xai @elonmusk Test details in comment
38M
echo.hive
@hive_echo
Jan 22, 2025
deepseek-r1 is now available in Cursor. Just go to settings>models> then click it on! 🥳 it won't work with the agent tho
178K
echo.hive
@hive_echo
Oct 26, 2025
I built a Continuous Attractor Network with 3 motor neurons which learn to guide the mice towards food using Reward‑modulated Hebbian plasticity No backpropagation and no SGD. In this case at first, the networked learned to circle around the food 😯 Source code is open
00:00
138K
echo.hive
@hive_echo
Oct 26, 2025
Spiking Neural Network from scratch achieves 8% accuracy. no backpropagation or SGD I created a genetic hyper parameter optimizer and it now, on average, can get 8% accuracy which is ~3% above chance Link to source code with a detailed video and markdown explanations in comment
00:00
00:27
echo.hive
@hive_echo
Oct 24, 2025
I built a biologically inspired spiking neural network from scratch and it learned with %5 accuracy to do addition :) There is no backpropagation, no artificial loss functions - just spikes, synapses, and dopamine-like reward signals. it uses STDP -> "Spike-Timing-Dependent
226K
echo.hive
@hive_echo
Jan 19, 2025
Memory systems for LLMs are easy 🥳 here are 5 implementations as objects 1) Vector memory 2) summary memory 3) time window memory 4) keyword memory 5) hierarchical memory 1)Vector Memory System ------------------- This memory system uses OpenAI's embeddings to create vector
79K
echo.hive
@hive_echo
Jan 26, 2025
deepseek-r1 multi-think script allows r1 to think in multiple as many different perspectives as you specify for a given question Code is in comment saves each perespective, thinking and response to JSON file. You can read a sample JSON in the comment Uses @openrouter
83K
echo.hive
@hive_echo
Mar 16, 2025
Sonnet MAX is coming to Cursor! What is it?
122K
echo.hive
@hive_echo
Dec 28, 2024
📚🤖 Open Source: AI reads PDFs Page-by-Page, extracts Knowledge & Summarizes 🥳 Repo in comment 💝 - 📚 Automated page by page PDF book analysis and knowledge extraction - 🤖 AI-powered content understanding and summarization - 📊 Interval-based progress summaries - 💾
00:00
82K
echo.hive
@hive_echo
Nov 26, 2024
2 Cursor Composer agents working together on the same project. one builds the project, the other reviews once the first agent is done and writes a report. cursor rules file is in comment to achieve this. first agent is instructed to build the project second agent is instructed
00:00
149K
echo.hive
@hive_echo
Aug 26, 2024
Learn Cursor in 5 minutes! Join my Cursor course which includes 17 videos building full apps from scratch with project files. Link in comment Repost this tweet and I will send the “how to build an AI scientist” video from my Cursor Course This will serve as an example taste
00:00
74K
echo.hive
@hive_echo
Apr 4, 2025
2 @cursor_ai agents in separate tabs chat and plan the most interesting app ever and build it too! collaboratively All you need is 2 rules, THAT IS IT! here is how: create 2 rule files set to "Manual" agent-1 .mdc: --- You are agent-1 you will be chatting with agent-2 to design
00:00
echo.hive
@hive_echo
Apr 1, 2025
if you think MCPs are complex and unnecessary for most things, you are not alone. here is a super simple way to give @cursor_ai any tools you want. Just create a tools . py file with functions which print their output write a super simple general. mdc file with super simple
89K
echo.hive
@hive_echo
Jan 23, 2025
1) Extract reasoning from DeepSeek-R1, 2) pass it to Sonnet-3.6, 3) and let it provide an answer with simulated reasoning Code in image Inspired by @skirano You can do this with any model and supercharge them with reasoning!! 🥳
00:38
Pietro Schirano
@skirano
Jan 22, 2025
By the way, you can extract JUST the reasoning from deepseek-reasoner, which means you can send that thinking process to any model you want before they answer you. Like here where I turn gpt-3.5 turbo into an absolute genius!
96K