Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

The Hacker News - Sep 23, 2026

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to date on our automated behavioral audit, our alignment suite that tests Claude across thousands

Read full article

More News

Science Tech Today

Provides daily Science and Technology news on scientific research with the hopes to invite and build a community to explore the multiple scientific research.

NEWSLETTER