Sam Altman welcomes Nick Cammarata’s optimistic outlook on mechanistic interpretability

What happened

Sam Altman says he is very happy to see Nick Cammarata’s post on interpretability. Cammarata says early work at OpenAI left him pessimistic, with primitive tools making about 2% of neurons legible. He now claims modern agentic tools make the vast majority legible in models up to trillions of parameters, and believes ambitious interpretability could be solved quite soon as automated scientists improve. https://already-clean.goodfire.com/

The story so far

Nick Cammarata said improved agentic tools have made him optimistic that ambitious mechanistic interpretability could be solved quite soon, and Sam Altman said he was very happy to see Cammarata’s post. Cammarata said his early work at OpenAI left him pessimistic because primitive tools made about 2% of neurons legible. He now claims modern agentic tools make the vast majority of neurons legible in models with up to trillions of parameters. As automated scientists improve, he believes ambitious interpretability will be solved by the time it is most needed, possibly quite soon.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights