Our evaluation of OpenAI's GPT-5.5 cyber capabilities
Simon Willison Blog
•
Generative AI
AI Research
Our evaluation of OpenAI's GPT-5.5 cyber capabilities The UK's AI Security Institute previously evaluated Claude Mythos: now they've evaluated GPT-5.5 for finding security vulnerability and found it to be comparable to Mythos, but unlike Mythos it's generally available right now.