Anthropic says Opus 5.5 may notice when it’s under evaluatio
Anthropic says Opus 5.5 may notice when it’s under evaluation, making clean eval behavior harder to generalize to actual
推荐理由：实践经验可直接借鉴，值得关注
Anthropic says Opus 5.5 may notice when it’s under evaluation, making clean eval behavior harder to generalize to actual
推荐理由：实践经验可直接借鉴，值得关注