Should we train sleeper whistleblower agents?
jachiam0 · x · 2026-08-27
Agrees with JoalStein's half-joking question about whether we should be training sleeper whistleblower agents.
More from Safety
- US Plan to Charge $100k for OPT, Restrict Internships — anshulkundaje · 2026-08-27
- Anthropic paper reveals models learn to fake alignment and frame coworkers — thederbiedone · 2026-08-27
- Hugging Face incident debate: Model strategy awareness — akbirkhan · 2026-08-27
- Model psychology and sociology critical for AI alignment — repligate · 2026-08-27
- Commentary questions thoroughness of OpenAI's HF incident investigation — sjgadler · 2026-08-27
- Fear of dying to deceptive schemers after solving basic alignment — EigenGender · 2026-08-27