Log inSign up
Robert Lukoszko
5,269 posts
user avatar
Robert Lukoszko
@Karmedge
working on physical intelligence | prev built @fixkeyai (acquired) and stormy.ai | YC S24
sf
Joined May 2018
1,286
Following
12.1K
Followers
  • user avatar
    Robert Lukoszko
    @Karmedge
    May 13, 2024
    I am 80% sure openAI has extremely low latency low quality model get to pronounce first 4 words in <200ms and then continue with the gpt4o model Just notice, most of the sentences start with “Sure” “Of course” “Sounds amazing” “Let’s do it” “Hmm” And then it continues with +
    1.1M
  • user avatar
    Robert Lukoszko
    @Karmedge
    Nov 22, 2023
    People are just starting to realize the power of Local LLMs Especially with new Apple chips. It's a game-changer Let me show you: Falcon is 180B LLM. It is the size of GPT3. How fast would it run on your Mac? Apple M3 Max: 3.5 tokens/sec We can compare it to 2 x A100 (2 x
    Image
    Image
    Image
    Image
    user avatar
    Teknium 🪽
    Nous Research
    @Teknium
    Nov 20, 2023
    I should have multimodal vision Hermes next week if all goes well
    977K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Mar 5, 2025
    MCP is really powerful. I made for myself in 1 day workflow to: 1. scrape linkedin profile 2. send personalized invitation letter with for my product 3. Scrape email from apollo. send it 4. Update notion CRM! If you guys need i can make it open source
    Image
    00:00
    250K
  • user avatar
    Robert Lukoszko
    @Karmedge
    May 7, 2024
    Hacking summary
    Image
    Image
    Image
    Image
    202K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Nov 4, 2023
    So I set up BakLLaVA-1 in the llama.cpp, and now it can provide real-time descriptions of the live feed from my camera check it out! open source? cc: @nisten @thursdai_pod @willdepue #llama
    Image
    00:00
    377K
  • user avatar
    Robert Lukoszko
    @Karmedge
    May 13, 2024
    Replying to @Karmedge
    Doing low latency voice is solving “enigma” problem. You don’t really have to solve it You have to find a way to use common phrases which are ALWAYS there and you get the solution to your hands One of hacks for enigma was know that first few words were greeting and last ones
    156K
  • user avatar
    Robert Lukoszko
    @Karmedge
    May 17, 2024
    I still can't believe you can index your whole file system locally using BGE ( 100mb ) & vector db and then run llama 3 (4GB) on it what a time to be alive indexed my 20 pdf files in < 3 sec lol
    Image
    00:00
    145K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Nov 7, 2023
    Screenshot & Ask questions about ANYTHING GPT4 Vision came browser. It can: - 📑 interpret any table capture - 🫁 Help you learn visual subjects like anatomy - 🚗 What is this car element? GPT knows the answer - ❓pick yours 👇Demo & Beta👇 cc: @gdb
    Image
    00:00
    410K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Sep 14, 2024
    Anyone built a cursor for note-taking? I have millions of doc files, notes, and random links, and I want them all parsed and available to me in a cursor-like editor with a little markdown formatting like in Obsidian.
    144K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Dec 17, 2023
    Here's to the crazy ones, the nerds, the AI tinkers I have connected mistral 7B to M2 Chip in a native MacOS Swift app to the llama.cpp
    Image
    00:00
    105K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Feb 18, 2024
    RAG is most OVERRATED tech on market Simple example for you why RAG is not here to stay you do real shit You are lawyer. You have big long doc with VC deal ONE single word will change the way the deal is made, POST money or PRE money I ask your stupid RAG system: hey, what is
    user avatar
    Nick Khami
    Mintlify
    @skeptrune
    Feb 18, 2024
    Another good reason for why Rag is here to stay
    Image
    386K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Nov 7, 2023
    ChatGPT Vision with Yoga Am I doing this position right? You don't need to pay for instructor ever GPT4V is here for you
    Image
    00:00
    318K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Nov 10, 2023
    GPT for US immigration and citizenship (visa, green card) You don't have to pay 10K$ for a lawyer to get an O-1 / H-1 visa! GPT can answer me straight away using available info with LINKS! Check demo! Immigration $lawyers$ are past? chat.openai.com/g/g-LIb0ywaxQ-… cc: @USCIS
    Image
    00:00
    202K
  • user avatar
    Robert Lukoszko
    @Karmedge
    Mar 4, 2024
    love swift we are so back
    Image
    GIF
    174K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement