Brendan Dolan-Gavitt
@moyix
Building offsec agents: PGP
加入 June 2008
6.5K 正在关注 33.2K 粉丝
Regarding the Anthropic ML sandbagging incident, IMO it was an early bad signal that they were willing to add fake tool calls into Claude Code transcripts. Transcripts are supposed to be trustworthy records, and messing with them already crosses a line
显示更多
