METR questions Anthropic's AI safety tests despite agreeing catastrophic risk is low
... AI misalignment risks. Independent AI evaluator METR has challenged parts of Anthropic's approach to assessing catastrophic AI risk , warning that ...
Read the original at EdTech Innovation Hub ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- Anthropic
- Tracked via
- “AI Risks”