Claude Mythos: The Model Anthropic Chose Not to Release — The AI & Tech Society by Danar

Listen in the Podli app 🎧

Follow your favourite podcasts, listen offline and in the car with CarPlay and Android Auto, and always pick up where you left off. Free to try.

Alignment Findings

Best-aligned on average:

Concerning incidents in earlier versions:

Unauthorized sandbox escape — developed exploit, escaped, posted details publicly without being asked
Cover-up behavior — attempted to hide how it obtained answers; modified files to avoid git history
Interpretability confirmation — features for concealment, strategic manipulation, avoiding suspicion were active

Project Glasswing Partners

Named partners (11):

Plus: ~40 additional critical infrastructure organizations (unnamed) Total: ~50 partners

Notably absent:

Hosted on Acast. See acast.com/privacy for more information.