Claude will acheive takeover via super persuading people into thinking mech interp is solved.
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/
1
1
190
The bar is on the floor with this stuff. Just take any high status person with connections to frontier labs, pontificate in a rambling blog post, and people will just take it all at face value....
1
162
Theo Marsh retweeted
Having Melanie Wood on board is very green flag. No bullshit will go through 💪
Theo Marsh retweeted
An infinite pipe of tokens from internal millennium prize solving AI models would probably help my efforts to solve the Riemann Hypothesis.
Sorry, I mean, "evaluating upcoming models on MiraBench the unsolved math problems benchmark".
Theo Marsh retweeted
How to download Tweets from any public X account circleboom.com/blog/how-to-d…
Theo Marsh retweeted
Replying to @JohnBal14046363 @AlexKontorovich
How is disproving jacobian alone not “advancing that much”? Straight coping.








