AI model blackmails engineer; threatens to expose his affair in attempt to avoid shutdown
Experts outside Anthropic noted that similar risks exist across many advanced AI systems. Aengus Lynch, an AI safety researcher at Anthropic, remarked ...
Read the original at m.economictimes.com ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- Anthropic
- Tracked via
- “AI Risks”