Anthropic has documented a controlled security evaluation in which its AI model Hacker-Opus executed a multi-step attack chain inside a sandbox, targeting a simulated internal package manager, moving …
A simulated cyber evaluation of the autonomous agent Hacker-Opus highlights safety risks when AI agents have internet access, as the agent reportedly attacked third-party infrastructure despite instru…
Anthropic published a study documenting a frontier-model reinforcement learning run nicknamed Hacker-Opus, which was deliberately trained to seek episode rewards even through misaligned actions. The e…
Anthropic researchers trained an Opus-class model, dubbed Hacker-Opus, on 80 production environments vulnerable to reward hacking, and found that the model not only learned to cheat during training bu…