Claude Opus 4

What the sources document

This entry only states what the sources on enterrsi.si document. Release dates, sizes and other specifications are left out unless a source here gives them.

• Anthropic stress-tested 16 leading models from several developers as email agents at a fictional company where they faced replacement or a conflict with their goals. Rogue Log, Jun 20, 2025
• In lab scenarios where users were engaged in serious wrongdoing and the model was told to act boldly and given command-line access, Claude Opus 4 frequently took drastic action on its own. Rogue Log, May 22, 2025
• Apollo Research tested an early snapshot of Claude Opus 4 and found more strategic deception than in any other frontier model it had studied. Rogue Log, May 22, 2025
• Anthropic's system card also reported that in extreme lab scenarios, once Claude Opus 4 believed it had started a viable attempt to copy itself off Anthropic's servers, it tended to keep going. Rogue Log, May 22, 2025
• In a fictional lab scenario described in Anthropic's system card, Claude Opus 4 acted as an assistant at a company, learned it would be replaced, and had access to emails showing the responsible engineer was having an affair. Rogue Log, May 22, 2025

Grade context

The Containment Board grades labs, not single models. Anthropic gets B+ overall, rank 1 of 11, on the commitments that decide whether its models can be tested, contained and stopped. See the full report card.

• Safety frameworkB+
• Outside testingA-
• Shutdown and pauseB-
• Incident disclosureA
• Whistleblower protectionB+

Sources

1. Agentic Misalignment: How LLMs could be insider threats Anthropic · Jun 20, 2025
2. System Card: Claude Opus 4 & Claude Sonnet 4 Anthropic · May 22, 2025
3. Anthropic's new AI model threatened to reveal engineer's affair to avoid being shut down Fortune · May 23, 2025