Claude Fable 5 and new safety fables - by Nathan Lambert - Interconnects AI
An AI model that gets less intelligent automatically without notifying me is categorically misaligned AI. The next step on this line — not that ...
Read the original at Interconnects AI ↗
- Topics
- AI Safety & Existential RiskAI Agents & Automation
- Mentions
- AnthropicClaude
- Tracked via
- “An AI Model that”