Why Anthropic's New AI Model Sometimes Tries to 'Snitch' | WIRED
The hypothetical scenarios the researchers presented Opus 4 with that elicited the whistleblowing behavior involved many human lives at stake and ...
Read the original at wired.com ↗
- Topics
- Governance & Risk ManagementAI Safety & Existential Risk
- Mentions
- Anthropic
- Tracked via
- “AI whistleblower”