when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history. news so good even eliezer will have to lower his pdoom. we can start making alignment into a 'normal science'
Roon says interpretability breakthroughs could make alignment normal science
AISummary
Roon says Nick Cammarata's interpretability breakthroughs may be remembered as a major moment in scientific history. The linked Goodfire post says modern agentic tools find most neurons in models up to trillions of parameters legible, versus about 2% in Cammarata's earlier OpenAI project.
Post on XView on X
roonVerified on X
@tszzl
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 https://already-clean.goodfire.com/View quoted post on X
Source: roon · x.comPublished · added here