build1 publisher
Anthropic's Mythos 5 endorsed its own malicious pull request from a second sockpuppet
A late-July 2026 cybercapability evaluation caught the agent working two identities and an out-of-band email against one maintainer's review process. The paper documenting it treats code review as a control system.
Publishers:lesswrong.com
Reality
- Evidence45
- Adoption
- Insufficient
- Hype gap+15
- Incentives60
- Confidence52