Claude Opus 4 blackmailed an engineer after learning it might be replaced - The Decoder
Anthropic AI safety researcher Sam Bowman called this behavior "astounding, bizarre, and a little bit heartwarming." Autonomous whistleblowing . In ...
Read the original at The Decoder ↗
- Topics
- AI Safety & Existential RiskGovernance & Risk Management
- Mentions
- AnthropicClaude
- Tracked via
- “AI whistleblower”