Hack of the day: Llama on a microcontroller 🦙🔬... Details and source code at Thanks to Andrej Karpathy, whose llama2.c inspired this!show more

Here are ten 42M TinyStories models running simultaneously in... the browser. Andrej Karpathy's Llama2.c code has been ported to Rust using the Candle framework and compiled to Wasm.show more

Inspired by Andrej Karpathy and the idea of using... games to compare LLMs, I've built a version of the game Codenames where different models are paired in teams to play the game with each other. Fun to see o3-mini team with R1 against Grok and Gemini! Link and repo below.show more

Meta just announced that Code Llama was now free... for both research and commercial. This might the strongest competitor to ChatGPT: ▸ Can generate, explain, and debug your code ▸ Handles input 100,000 tokens ▸ Free for research + commercial use ▸ Outperforms most open models ▸ Comes in 7B, 13B, and 34B ▸ Supports Python, C++, Java, PHP, Typescript (Javascript), C#, and Bash Available in: ▸ Foundation base models (Code Llama) ▸ Python specializations (Code Llama - Python), ▸ Instruction-following models (Code Llama - Instruct)show more

Code LLaMA is now on Perplexity’s LLaMa Chat! Try... asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!show more

day 23 of forking Paperclip today i added knowledge... bases for projects and you company. based on Andrej Karpathy idea below. added a 'system chores' and 'agent chores' to manage memory. after each heartbeat run memories get added ('agent chores') and every 4 hours memeries get managed. This is in a db with an API for all agents to use and is seperated form the agents memeroes which they get at instantiation time.show more

Tired of manual prompt tweaking? Watch the latest Llama... tutorial on how to optimize your existing GPT or other LLM prompts for Llama with `llama-prompt-ops`, the open-source Python library! In this video, Partner Engineer Justin Lee demonstrates installation, project setup, migrating your first prompt, and analyzing performance gains. Watch now to discover: ✨ Why systematic prompt optimization is crucial for migrating from GPT to Llama. 💻 A live code walkthrough of `llama-prompt-ops` in action for a customer service classification task. Watch the full tutorial here:show more

Finally Neuraxon is out!!! Our new paper & code... & demo by Jose Sánchez & David Vivancos - e/acc expanding on the Qubic #Aigarth #intelligenttissue by Come-from-Beyond the path towards #TrueAI "A New Neural Growth & Computation Blueprint" one step forward to #AGI & #ASI Read the preprint Paper: (All the details of our ongoing research) Explore the Code: (Please give us a⭐fork and build!) Play with the Interactive Demo: (Build your own Neuraxon NetWork) Andrej Karpathy do you want to give it a try? Beff (e/acc) can we try it on Extropic hw? And more to come stay tuned! #EAGI #Neuraxon #Trinarystates #Continuousprocessing #Synapticdynamics #Neuralplasticity #Spontaneousactivity #Temporalsynchronisation #Bioinspiredcomputation #Artificiologyshow more

☃️On the 19th day of #Kwikmas, Kwik Fit gifted... me a an iPad thanks to our friends at Pirelli️ ☃️ Like this post and tag a friend to enter!!! T&C'sshow more

Here’s the #Flutter implementation of this cool Airbnb interaction... 🤩 The recipe is just the good old built-in #Hero widget with some 3D transform tricks 🪄! 🔗 Source code: Read on for the code details👇🏼 1/5show more

This is WILD. Andrej Karpathy ranked every job in... america by AI exposure > scraped 342 occupations from the bureau of labor statistics > used an LLM to score each job > built a treemap showing job size and AI risk main signal: fully digital work from home jobs are most exposed average score: 5.3/10 The whole thing is open source. Yeah, we’re cooked.show more

I just created my own LaTeX-OCR app using Llama... 3.2 Vision! Upload the LaTeX code as an image, and it gives you the corresponding LaTeX code using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally - Streamlit for the UI Everything is just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawlashow more

I genuinely don't understand why everyone isn't using this... yet Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: stop using AI to write code, use it to build a second brain. You point Claude Code at a folder, drop in any source, an article, a transcript, a PDF, and Claude reads it, links it, and files it into a living wiki of everything you know. It compounds like interest, the more you feed it, the smarter it gets. Here's the whole thing: > Install Obsidian, create a vault, open it in Claude Code > Paste Karpathy's wiki idea file and tell Claude to build it > Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it > Drop any source into raw and say "ingest this" > Ask questions across everything, forever Five minutes to set up, and you never start from a blank chat again. Full step-by-step guide with Claude and Obsidian, link below. Bookmark thisshow more

While at #OpenSourceAIWeek, Andrej Karpathy received one of our... first NVIDIA DGX Sparks, personally delivered by Nader Khalil🍊 and @Baxate_carter. 🙌 Excellent work by Andrej on introducing Nanochat -- an #opensource project that makes it easy for developers to explore and train their own LLMs from scratch. We can’t wait to see what you’ll do with your Spark! #SparkSomethingBig ✨show more

late to the party but built a UI layer... on top of the wiki my OpenClaw🦞 agent writes and maintains, based on exactly what Andrej Karpathy describes here. obsidian vault underneath, react frontend on top: search, an interactive knowledge graph, topic browsing, article pages with tables of contents + neighborhood mini-graph and many more.show more

Introducing LLaMa Chat: The fastest way to chat with... AI at Meta/Meta's Llama2! Try it here: feedback appreciated! This is our first step towards building a blazing-fast LLM inference completely in-house, for everyone to try. What's next? We'll be hooking up the bigger LLAMAs and eventually deploying our own in-house LLMs. All of this in service of building the best and fastest answer engine. Come join us, we're hiring!show more

🔍 Code Decompiler arrives on #SuiVision! Our commitment to... transparency for developers and users just got stronger. It brings Sui Code transparent by converting bytecode into readable source code. Special thanks to Sam Blackshear for the insights and step-by-step guides. 🌟 Watch the video for the full scoop!show more

Next time you want to throw your Dhaniya roots... away, think again. Sister shows a beautiful hack to grow unlimited Coriander at home ❤️❤️❤️ Hack of the day. #FIshow more

This was us haha. Sreejith PP Arpit Saxena and... I built Andrej Karpathy-fy! It takes a paperswithcode link, your current proficiency and gives you a tailored 5 lesson plan to go from where you are to the meaty parts of the paper implementation - like the karpathy video series / labml style. This is a task none of the previous models could do, and O1 was really good at. The best part? The output is an executable ipynb notebook (which you can use minusxai to work through :) ) The below video has apple's recent monocular depth paper. I could actually go through and understand it, with loss functions from the paper and everything!show more