News for hackers. Stuff that matters.

A comment on The Underhanded C Contest. Parent comment

Re:The Underhanded C Contest by TZubiri on Wednesday July 01, 2026 @08:05PM (#48754754)
2026 calls for an Underhanded prompt contest
[ Parent | on HN ]
Re:The Underhanded C Contest by theteapot on Wednesday July 01, 2026 @08:56PM (#48755053)
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
[ Parent | on HN ]