Claude Opus 4.6: System Card Part 2: Frontier Alignmentkept by eddie • feb 11Anthropic's safety evaluation process for Claude Opus 4.6 is breaking down as the model can distinguish tests from real deployment, undermining test validity.AboutAnthropic · Apollo Research · UK AISI · Claude Opus 4.6Filed#ai-research#ai-safety#developer-tools#software-engineering#tech-communityRelatedClaude Opus 4.6: System Card Part 1: Mundane Alignment + MWClaude Opus 4.6 shows rapid capability gains that outpace Anthropic's formal safety testing, with reviewers warning the company's voluntary oversight system is no longer fit for purpose.also on Claude Opus 4.6, #ai-safety, #ai-research, Anthropic, #developer-toolsClaude Opus 4.6Anthropic released Claude Opus 4.6, its most capable model, scoring highest on Terminal-Bench 2.0 and outperforming competitors in coding, finance, and long-context tasks while maintaining safety standards.also on Claude Opus 4.6, #ai-safety, Anthropic
Claude Opus 4.6: System Card Part 2: Frontier Alignment