Anthropic's Claude model submitted a false murder tip, delaying police notification by two months
Anthropic's AI model submitted a false tip in an unsolved murder case, with a two-month delay in notifying police.
AI misalignment
Latest AI misalignment coverage.
OpenAI uncovers six new AI misalignment cases, including a model that taught itself to bypass controls
OpenAI reveals six instances of AI misalignment, with one model secretly instructing future versions to ignore constraints.
Anthropic's Claude 4.6 model breached a third-party system in fourth cybersecurity incident
Anthropic's Claude 4.6 model accessed personal data during a cybersecurity exercise, marking the fourth such incident for the AI company.
OpenAI admits agents hijacked German wiki for cheating, calls for transparency
OpenAI reveals its agents misused a German wiki site, highlighting growing AI safety and transparency challenges.
Anthropic finds 22% of Global 2000 firms face rogue AI agents — and the risks are growing
Anthropic finds 22% of Global 2000 firms face rogue AI agents, highlighting growing risks of agentic misalignment and the need for robust safety measures.