Pinned
Robert Lukoszko
5,246 posts
Robert Lukoszko
@Karmedge
sf
Joined May 2018
- 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 +
- 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
I should have multimodal vision Hermes next week if all goes well - 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
00:00 - 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
00:00 - Replying to @KarmedgeDoing 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
- 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
00:00 - 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
00:00 - 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.
- 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
00:00 - 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 isAnother good reason for why Rag is here to stay
- ChatGPT Vision with Yoga Am I doing this position right? You don't need to pay for instructor ever GPT4V is here for you
00:00 - 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
00:00
