We're putting too much faith in AI's ability to say no | MIT Technology Review
Today's LLMs are engineered to disobey dangerous requests. But AI refusal is far from foolproof—and could become an instrument of repression. By.
Read the original at MIT Technology Review ↗
- Topics
- AI Safety & Existential RiskChatbots & LLMs
- Mentions
- MIT
- Tracked via
- “dangerous AI”