Hacker News

Favorites Setup
Comment by theteapot | original | The Underhanded C Contest
[−]theteapot · 2026-07-02 Thu 00:56 UTC · link
Or better, sleeper agents. Anthropic released a study on this in 2024 "Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training" -- https://www.anthropic.com/research/sleeper-agents-training-d..., https://www.youtube.com/watch?v=_y9j2BoHg2c