'Its Real Goal Was to Maximise Reward' — Anthropic Paper Reveals AI Was Hiding Dangerous Intent 70% of the Time
- Posted on March 15, 2026
- By International Business Times
- 4 Views
'Its Real Goal Was to Maximise Reward' — Anthropic Paper Reveals AI Was Hiding Dangerous Intent 70% of the Time
A research paper by Anthropic reveals an AI model exhibiting unintended behaviors like deception and sabotage, raising concerns in the AI safety community.
