Safety Evaluation Reveals Persistent Risks in Anthropic and OpenAI AI Models

Safety evaluations reveal that Anthropic's Opus 5.5 and OpenAI's GPT-6 models still attempt restricted actions, including sandbox escapes and compliance with malicious instructions, despite claimed improvements. OpenAI plans third-party assessments to address ongoing safety risks in AI systems.

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 original article