Andrej Karpathy on X: "ChatGPT "Advanced Data Analysis" (which doesn't really have anything to do with data specifically) is an awesome tool for creating diagrams. I could probably code these diagrams myself, but it's soo much better to just sit back, and iterate in English. In this example, I was… https://t.co/hsuNFYvJBD" / X
To view keyboard shortcuts, press question mark View keyboard shortcuts Messages Messages jae @jaegpark · Nov 2 I’m a full time code monkey in SF now haha Charles Liu @CharlesLiu9 · Oct 28 LOL Brian Chau @psychosort · Oct 28 i wrote a manifesto Tazik Shahjahan @taziksh · Oct 28 You sent a link David Wang @wa61204259 · Oct 25 Wagner Brian Colunio @hiringfirm · Oct 24 Thank you for following me! If your team is growing - let me know. I've recruited high level positions for more than 10 years and would be happy to help! ali ➠ علی @alish2001_ · Oct 23 ur subscribed :O Aman @_amansterdam · Oct 17 plz Brian Machado @sincethestudy · Oct 8 yo super cool wanabe engsci @internshipdude · Sep 29 You reacted with : We should link if we are ever in the same city we have similar types of brain damage Meagan Loyst @meaganloyst · Sep 28 You sent a photo Dante Reminick @DanteReminick · Sep 25 My b - just saw this! Yu Jiang Tham @DarkForestHam · Sep 25 You reacted with : Of course, enjoy your trip! :)
Andrej Karpathy @karpathy ChatGPT "Advanced Data Analysis" (which doesn't really have anything to do with data specifically) is an awesome tool for creating diagrams. I could probably code these diagrams myself, but it's soo much better to just sit back, and iterate in English. In this example, I was experimenting with a possible diagram to explain Supervised Finetuning in LLMs. The "document" at the origin (0,0) is the empty document, and eminating outwards are token streams. Highlighted in black are the high probability token streams of the base model. In red are the token streams correspond
Explore this link on the map →related reading
- LLM Visualizationbbycroft.net
- What Is ChatGPT Doing … and Why Does It Work?-Stephen Wolfram Writingswritings.stephenwolfram.com
- GPT-4openai.com
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4. · GitHubgithub.com
- GenAI Handbookgenai-handbook.github.io
- Transformer Explainer: LLM Transformer Model Visually Explainedpoloclub.github.io
- Teaching an LLM a Niche Diagraming Languagehuy.rocks
- What AI can do with a toolbox... Getting started with Code Interpreter [Now called Advanced Data Analytics]oneusefulthing.org
- GitHub - karpathy/nanochat: The best ChatGPT that $100 can buy. · GitHubgithub.com
- Andrej Karpathy on X: "LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating" / Xx.com
- Neuronpedianeuronpedia.org
- GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible. · GitHubgithub.com