System Card: Claude Mythos Preview [pdf]

Post by mbesto » Thu, Apr 09, 2026, 6:23 PM UTC

pants2 wrote: post #13

babelfish wrote: post #3

Combined results (Claude Mythos / Claude Opus 4.6 / GPT-5.4 / Gemini 3.1 Pro) SWE-bench Verified: 93.9% / 80.8% / — / 80.6% SWE-bench Pro: 77.8% / 53.4% / 57.7% / 54.2% SWE-bench Multilingual: 87.3% / 77.8% / — / — SWE-bench Multimodal: 59.0% / 27.1% / — / — Terminal-Bench 2.0: 82.0% / 65.4% / 75.1% / 68.5% GPQA Diamond: 94.5% / 91.3% / 92.8% / 94.3% MMMLU: 92.7% / 91.1% / — / 92.6–93.6% USAMO: 97.6% / 42.3% / 95.2%…

We're gonna need some new benchmarks... ARC-AGI-3 might be the only remaining benchmark below 50%

Post by bluerooibos » Thu, Apr 09, 2026, 8:43 PM UTC

kypro wrote: post #165

Cool on not publicly releasing it. I would assume they've also not connected it to the internet yet? If they have I guess humanity should just keep our collective fingers crossed that they haven't created a model quite capable of escaping yet, or if it is, and may have escaped, lets hope it has no goals of it's own that are incompatible with our own. Also, maybe lets not continue running this experiment to see how fa…

Post by jph00 » Thu, Apr 09, 2026, 9:05 PM UTC

stratos123 wrote: post #510

jph00 wrote: post #106

Earlier quoted context omitted.

Yeah this has always been the glaring blind spot for most of the "AI Safety" community; and most of the proposals for "improving" AI safety actually make these risks far worse and far more likely.

It makes quite a lot of sense to focus on reducing the risks of every human everywhere dying, rather than the risks of already existing oppression getting worse.

Post by jjcm » Thu, Apr 09, 2026, 11:32 PM UTC

ayewo wrote: post #588

jjcm wrote: post #444

Earlier quoted context omitted.

I read the entire thing fwiw (pseudo-retired life helps with time here). It looks like it was a collaborative effort across multiple teams, where each team (research, security, psycology, etc etc etc) were all submitting ~10 pages or so. It doesn't feel like slop.

Did anything stand out across those 244 pages? Perhaps you have some of your take away thoughts written up somewhere?

Post by amunozo » Fri, Apr 10, 2026, 12:02 PM UTC

stavros wrote: post #656

amunozo wrote: post #654

Earlier quoted context omitted.

Why couldn't it be unknowable? I am not saying that it is, but it could be. The human brain has its limits and things could me too complex for us to understand enough to be able to modify them at will. We could understand a lot, but not enough to manipulate it with certainty. Biology is not physics.

Because physics is knowable, and I don't think an unknowable thing can be created from a knowable thing.