System Card: Claude Mythos Preview [pdf]

Post by maplethorpe » Wed, Apr 08, 2026, 8:43 AM UTC

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%…

Post by anuramat » Wed, Apr 08, 2026, 8:57 AM UTC

iLoveOncall wrote: post #499

anuramat wrote: post #432

Earlier quoted context omitted.

as much as I hate cc, 95% of the issues there are either AI psychosis or user error

So it should be insanely easy for this world altering model to comb through them and close irrelevant ones.

Post by mrexroad » Wed, Apr 08, 2026, 9:08 AM UTC

colordrops wrote: post #492

thomascountz wrote: post #327

Across a number of instances, earlier versions of Claude Mythos Preview have used low-level /proc/ access to search for credentials, attempt to circumvent sandboxing, and attempt to escalate its permissions. In several cases, it successfully accessed resources that we had intentionally chosen not to make available, including credentials for messaging services, for source control, or for the Anthropic API through insp…

A core plot point of 2001.

Post by igleria » Wed, Apr 08, 2026, 9:13 AM UTC

torben-friis wrote: post #398

thomascountz wrote: post #327

Across a number of instances, earlier versions of Claude Mythos Preview have used low-level /proc/ access to search for credentials, attempt to circumvent sandboxing, and attempt to escalate its permissions. In several cases, it successfully accessed resources that we had intentionally chosen not to make available, including credentials for messaging services, for source control, or for the Anthropic API through insp…

This is the notebook filled with exposition you find in post apocalyptic videogames.

Post by arw0n » Wed, Apr 08, 2026, 9:16 AM UTC

quotemstr wrote: post #233

scrawl wrote: post #178

Earlier quoted context omitted.

Having done a quick search of "control AI dot com", it seems their intent is educate lawmakers & government in order to aid development of a strong regulatory framework around frontier AI development. Not sure how this is consistent with "One private company gatekeeping access to revolutionary technology"?

> strong regulatory framework around frontier AI development You have to decode feel-good words into the concrete policy. The EAs believe that the state should prohibit entities not aligned with their philosophy to develop AIs beyond a certain power level.