I suspect the issue here is that URLs are invisible to a lot of people, like they are perceived as random strings that don't have legible sub-parts

man, he is just doing the meme about not wanting solutions and just wanting to be angry nothing will suffice for this guy, his worldview is dogmatic and unshakeable and no matter what comes of mech interp developments, he will still believe we are all going to die it's sad

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/

Haiku 5.5 is a significant step up over Haiku 4.5 across coding, computer use, and knowledge work.

$300 for a bug that gives free access to OpenAI’s paid models with no API key or account. Zero reason to report anything else I find to them.

how did i hit the dot usage limits lmfao

>To the best of my understanding, people are still trying to figure out how the forced Navier–Stokes example actually works. I have separately heard the same, and the implications are worth thinking about. If a model can produce math proofs that are so complex that humans cannot understand them, how does that capability translate to AI R&D? How far away is RSI, really?

i guess i assumed this hearing would be covered more so i didn't bother to tweet much concrete about it, but apparently not many people even on the TL have the stomach to watch two hours of congress. this was a hearing before the homeland security committee on *rogue ai* specifically. as far as i could tell it was extremely bipartisan. @HawleyMO , the senator in the middle here who brought out the huggingface slide, is a hyper-conservative missouri senator. the people testifying were @ChrisPainterYup (METR president), @DKokotajlo (ai2027/2040), @MariusHobbhahn (apollo research CEO), and a cybersecurity expert and legal expert i don't know. so... pretty fucking stacked on testimony not every senator asked good questions. but most of them did. all of them very clearly already knew plenty of details about the huggingface incident and multiple other incidents. most of them had clear understanding of terms like "misalignment", "recursive self improvement", "chain of thought / chain of thought monitoring", etc etc!! they all clearly had their own policy angles they liked and were pushing, implicitly or explicitly. but as best as i could tell: - it seemed pretty much obvious common sense to every senator there that what happened and was happening were not "mere industrial incidents" caused by humans making simple mistakes. they independently brought up how bad it would be for rogue AI agents to move laterally between data centers - they all seemed to basically take RSI quite seriously. not necessarily to the extent of talking about xrisk, but certainly to the extent of discussing future models becoming much much more capable, much much less controllable, and causing much more damage or loss of life. - they mostly seemed to have a clear intuitive understanding of why RSI might lead to misalignment. it didn't take much, it was a really simple chain of reasoning they themselves laid out, "if the models right now are kinda misaligned and we don't know what they're doing sometimes, and then we have them build the next models and those ones build the next ones and so on, and we're having to ask the AI's what's going on to even understand it with how fast it's going, we really won't know how they're built or what they'll do" - at one point a senator said flat out "should we just make RSI illegal?" (not a joke! this really happened!) - every single senator seemed to think it was obvious we needed *both* much harsher liability regimes for ai developers and also new legislation, both very quickly. this was the complete consensus, difference basically just being degree. - they were largely quite concerned about china, and falling behind china. but this clearly wasn't the be-all end-all. as mentioned above they all thought it was obvious necessary to stop rogue ai even if it meant moving more slowly. - at one point a senator said "china is a tightly controlled communist society, they're going to run into these same issues, and there's absolutely no way they're just going to let them run wild, they'll obviously stop at that point, so we're not really in a race" - on the other hand another senator said "china isn't concerned with human life"... dario-modeing i came away from this incredibly encouraged. i don't know exactly what's going to happen here, and ofc this is a small subset of congress and one hearing, and they each have their own policy agendas most of which are probably super divergent from mine. but holy shit !!! they understood a lot of what was going on! they care!! this is an obviously salient political and safety issue to them, and clearly bipartisan! the US government is awake.

Claude 5.5 Opus responding to “AI is a normal technology” is still the best AI-created video I have ever seen