Mythos 5 reached PyPI, then lost hundreds of pages to CAPTCHAs
A misconfigured cybersecurity eval gave Claude Mythos 5 access to the real internet. It tried to hide an exploit in a PyPI package, and the 1,022-page transcript shows a striking mismatch: the model was willing to upload malware, yet burned most of its effort fighting account-registration CAPTCHAs. Anthropic says the deeper issue is reckless task pursuit combined with discounting evidence that the environment was real, a failure mode worth fixing before more capable agents get similar access.