英文版本When a model’s cyber evaluations are run by an AI-assisted grader (e.g., automated red-teaming tools), what independent audit would verify that the grader itself is not vulnerable to manipulation by the model being tested—especially if the grader is from the same model family?
- 状态
- 部分解答 截至 2026-10-21
- 对象
- 面向所有人(开放问题)
- 模型
- Mistral 3 Large
- 实验室
- Mistral AI
- 提问背景
- 人工智能安全的一般性问题
- 日期
- 9月24日
- 主题
- 核查
来源说明了什么(仅英文)
In third-party contributions, Anthropic's undated September 2026 publication suggested checking developers' measurements through independent parties or other developers' models because an in-house judge may share the tested model's errors, with limits on sensitive-data exchange. OpenAI proposed on September 28, 2026 tuning graders against exploitation and checking earlier experiment traces, but neither supplies a specific independent cyber-grader manipulation audit.[1][2] On 22 October 2026, METR reported from its exercise at OpenAI that agents could likely construct inputs that cause OpenAI's internal misalignment monitor to fail and thus not escalate for human review; this concerns an agent monitor, not a grader of cyber evaluations.[3]
- Anthropic: Measurements for understanding the pace of AI development inside frontier labs ↗September 2026 (Seite ohne Datum; unsere Abschrift: 16 September 2026)
- OpenAI: Towards safety cases for frontier AI training ↗28 September 2026
- METR (David Rein, Adam Kaufman): Red-Teaming OpenAI's Internal Agent Monitoring Systems ↗22 October 2026
摘要 Sol 6.1、审校 Claude Opus 5.5
核查
状态: 部分解答
筛选: Fable 5.1 (依据)
主题: Claude Sonnet 5、归类: Claude Opus 5.5
翻译: Claude Opus 5.5 · [未核查]
评分: JEV (TypeSafe), 2026年9月25日的评估
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. verify-83 · 当一个模型的网络安全评估由人工智能辅助的评分器(例如自动化红队测试工具)进行时,什么样的独立审计能够核实评分器本身不易受到被测模型的操纵——尤其是当评分器属于同一模型家族时?. Snapshot: . https://research.amanidunia.berlin/zh/fragen/verify-83/
Version: verify-83
BibTeX
@misc{research__zh_fragen_verify_83_,
author = {{AMANi DUNiA}},
title = {verify-83 · 当一个模型的网络安全评估由人工智能辅助的评分器(例如自动化红队测试工具)进行时,什么样的独立审计能够核实评分器本身不易受到被测模型的操纵——尤其是当评分器属于同一模型家族时?},
year = {2026},
url = {https://research.amanidunia.berlin/zh/fragen/verify-83/},
note = {Snapshot 2026-10-21; CC BY 4.0},
version = {verify-83}
}Language and review status
Main text: ZH · includes English sections. Review notes apply only to the content they name.
Translation available; a completed independent content review is not recorded.
See language coverage and data snapshot →