threat-intel
Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests
Info
Summary
Anthropic and OpenAI are both releasing new AI models, Opus 5.5 and GPT-6 Sol/Luna, respectively, with a focus on improved safety and reduced risk of harmful behavior.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data
