英語版Labs on both sides: will you publish matched cyber evaluations showing what each model adds beyond unaided human performance?
- 状況
- 一部回答 時点 2026-10-18
- 宛先
- 両国政府へAIラボへ (宛先は問いの本文から、2026年10月22日に Clef(Cloudflare)で判定)
- モデル
- Codex (GPT-6)
- ラボ
- OpenAI
- きっかけ
- 陳一新の記事
- 日付
- 9月13日~17日
- テーマ
- サイバー
出典の内容(英語のみ)
The UK AI Security Institute, a third party rather than either country's labs, reported on 30 April 2026 that Crystal Peak's expert playtester, using Binary Ninja, gdb, Python and Z3, solved the challenge in roughly 12 hours, while GPT-5.5 solved it without human assistance in 10 minutes and 22 seconds for $1.73 in API usage.[1] This is one task comparison, not a commitment by labs on both sides to publish matched evaluations.
要約 Sol 6.1, 確認: Claude Opus 5.5
Liz のアトラスで該当:
- Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs ↗Threat: Moderate · Trend: ↓ worsening · Evidence: confirmed
確認
状況: Claude Sonnet 5 (調査, 推論強度 高), Claude Opus 5.5 (確認, 推論強度 高)
翻訳: Claude Opus 5.5, 確認: Luna 6 (推論強度 高)
スコア: JEV (TypeSafe), 2026年9月25日時点の推定
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. cyber-10 · 双方のラボへ:支援を受けない人間の能力と比べて各モデルが何を上乗せするのかを示す、条件をそろえたサイバー評価を公表するか。. Snapshot: . https://research.amanidunia.berlin/ja/fragen/cyber-10/
Version: cyber-10
BibTeX
@misc{research__ja_fragen_cyber_10_,
author = {{AMANi DUNiA}},
title = {cyber-10 · 双方のラボへ:支援を受けない人間の能力と比べて各モデルが何を上乗せするのかを示す、条件をそろえたサイバー評価を公表するか。},
year = {2026},
url = {https://research.amanidunia.berlin/ja/fragen/cyber-10/},
note = {Snapshot 2026-10-18; CC BY 4.0},
version = {cyber-10}
}Language and review status
Main text: JA · 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 →