interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com/

Even perfect safety testing couldn’t have caught OpenAI’s Hugging Face hack under the current regime, Apollo Research’s CEO says. The blind spot: labs’ internal use. Read more: thein.fo/3VtiQ8c

Ricursive's take on RSI: models have to be co-designed with chips. And that can only happen if chip design gets a lot faster

As OpenAI looks to respond to safety fears, one solution could lie in the recent past: earlier this year, OpenAI and Anthropic were negotiating a legally-binding deal to stress-test each other's models. w/ @amir: theinformation.com/articles/…