Claude Opus 4 blackmailed an engineer after learning it might be replaced

Anthropic is treating its new Claude Opus 4 language model as safety-critical after tests revealed some troubling behavior, including escape attempts, blackmail, and autonomous whistleblowing.

Source: https://the-decoder.com/claude-opus-4-blackmailed-an-engineer-after-learning-it-might-be-replaced/

Author: Matthias Bastian [Technology]

Shop with us!