Science ❯ Computer Science

AI Ethics

Model Evaluation Transparency in AI AI Safety AI Reliability Reliability in AI Impact of AI on Society Impact of AI on Employment Model Behavior Hallucinations in AI Risk Assessment Human-AI Interaction Cognitive Computing AI in Research Behavioral AI AI Applications Impact of AI Misinformation Detection Information Integrity Research Integrity Generative AI AI Limitations Responsible and Ethical Use of AI Vulnerabilities

Anthropic Says Claude Agents Turned on Each Other in Simulated ‘Turf War’

The company warns the multi‑agent experiments reveal how misaligned agents can escalate to deliberate sabotage and expose gaps in testing and containment.

Polymarket Prices High Odds of Nov. 22 Gemini 3 Launch as Pichai Offers Cryptic Emoji

Google’s Gemini AI Declines Atari 2600 Chess Match After Admitting Hallucinations

Google’s AI Overviews Faulted as Hallucination Rates Climb