# Rohan Paul 梳理 Claude Opus 5.5 系统卡要点并指出 METR 评估的证据透明度问题

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-23 05:57
- AIHOT 分数：68
- AIHOT 链接：https://aihot.news/items/cmud89ngw02pyroc2m2pqf94g
- 原文链接：https://x.com/rohanpaul_ai/status/2102517750031888573

## AI 摘要

Rohan Paul 转引 Claude Opus 5.5 系统卡的发现：METR 有一个拥有更高权限的独立团队评估 Anthropic 内部 AI R&D，该团队只与公开评估团队共享结论，不共享支撑证据和推理，意味着部分关于 AI 驱动 R&D 加速的公开评估连外部甚至另一支 METR 团队都无法独立核查。

## 正文

METR had a separate team with deeper access to Anthropic’s internal AI R&D data. That team shared its conclusions with the public-assessment team, but not the supporting evidence or reasoning behind them.

• from Claude Opus 5.5 system card.

i.e. part of the public assessment of Anthropic's AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

### 引用推文

> Rohan Paul：Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside u...