AI pioneer announces non-profit to develop 'honest' artificial intelligence - The Guardian
Deployed alongside an AI agent, Bengio's model would flag potentially harmful behaviour by an autonomous system – having gauged the probability of its ...
Read the original at The Guardian ↗
- Topics
- AI Safety & Existential RiskAI Agents & Automation
- Mentions
- Yoshua Bengio
- Tracked via
- “dangerous AI”