Anthropic details unreleased Model 2, new alignment concerns in latest AI risk report
Threat Model 2 encompasses smaller hazards . In particular, it covers situations where an AI model with access to an organization's systems tempers ...
Read the original at SiliconANGLE ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- Anthropic
- Tracked via
- “AI Risks”