| ▲ | TZubiri 7 hours ago | |
2026 calls for an Underhanded prompt contest | ||
| ▲ | theteapot 7 hours ago | parent [-] | |
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 | ||