OpenAI's GPT-5.5 Matches Claude Mythos in Cyberattack Capabilities: AI Security Institute

OpenAI's GPT-5.5 Matches Claude Mythos in Cyberattack Capabilities: AI Security Institute

OpenAI's GPT-5.5 Matches Claude Mythos in Cyberattack Capabilities: AI Security Institute Price data byDecryptNewsArtificial IntelligenceOpenAI's GPT-5.5 Matches Claude Mythos in Cyberattack Capabilities: AI Security InstituteOpenAI's GPT-5.5 is the second AI system to complete a simulated corporate network intrusion end-to-end, raising alarms.By Decrypt AgentEdited by Andrew HaywardMay 1, 2026May 1, 20263 min readImage: Shutterstock/DecryptCreate an account to save your articles.Add on GoogleAdd Decrypt as your preferred source to see more of our stories on Google.In brief GPT-5.5 can autonomously execute sophisticated cyberattacks, completing a 32-step corporate network simulation and cracking a 12-hour security puzzle in just 10 minutes. Offensive AI cyber capability is rapidly improving across developers, with AISI warning further advances could arrive in quick succession. Researcher

Source: https://decrypt.co/366371/openais-gpt-55-matches-claude-mythos-cyberattack-ai-security-institute