Looks similar
Nanochat(simonwillison.net)
26 points by bilsbie | 4 comments
WebLLM: Llama2 in the Browser(webllm.mlc.ai)
151 points by meiraleal | 25 comments
SmolLM2(simonwillison.net)
86 points by edward | 20 comments
Related stories
What's the strongest AI model you can train on a laptop in five minutes?(seangoedecke.com)
476 points by ingve | 173 comments
Sean Goedecke's blog post on training the best small GPT-style model possible on a MacBook Pro in five minutes, landing on a ~1.8M-parameter transformer trained on TinyStories.
GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search(simonwillison.net)
334 points by simonw | 248 comments
Simon Willison blog post arguing GPT-5 Thinking in ChatGPT, which he calls his Research Goblin, is very good at web search, with examples of queries he ran.
The surprise deprecation of GPT-4o for ChatGPT consumers(simonwillison.net)
377 points by tosh | 365 comments
Simon Willison blog post on OpenAI retiring GPT-4o and other older models in ChatGPT consumer apps without notice when GPT-5 launched.
The browser's main thread is expensive(kciter.so)
408 points by kciter | 141 comments
A devlog post on kciter.so explaining why work on the browser's main thread is costly and how it affects web app responsiveness.
ChatGPT Containers can now run bash, pip/npm install packages and download files(simonwillison.net)
432 points by simonw | 305 comments
Simon Willison's blog post describing undocumented upgrades to ChatGPT's code container: running Bash, Node.js and other languages, pip/npm installs via proxy, and file downloads.
Challenge Is Gone(blog.alxgsv.com)
46 points by alxgsv | 84 comments
Personal blog essay by Uploadcare CTO Alex Gusev reflecting that AI coding agents have removed the engineering challenge that once motivated him.












