英語版What concrete capability thresholds should trigger a mandatory pause and external review before agent systems are deployed?
- 状況
- 一部回答 時点 2026-10-01
- 宛先
- AIラボへテーマ別 · JEV (問いに宛先がなく、テーマで割り当て)
- モデル
- Gemini 3.8 Flash
- ラボ
- 日付
- 9月12日~20日
- テーマ
- レッドライン
出典の内容(英語のみ)
On 28 September 2026, OpenAI said it had paused tool-use training and evaluation for its most capable models until additional safeguards were in place.[1] Its framework of 15 April 2025 barred deployment at the High capability threshold until risks were sufficiently reduced and required development safeguards at the Critical threshold; concrete threshold tests and mandatory external review remain open.[2]
- OpenAI: How we will do better for Australia ↗2026-09-28
- OpenAI: Preparedness Framework, Version 2 (Last updated 15 April 2025) ↗2025-04-15
要約 Sol 6.1, 確認: Claude Opus 5.5
Liz のアトラスで該当:
- Agentic LLMs Pose Novel Risks ↗Threat: High · Trend: ↓ worsening · Evidence: confirmed
- Emergent capabilities unpredictability ↗Threat: Open problem · Trend: → steady · Evidence: contested
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. redlines-02 · エージェントシステムのデプロイ前に、義務的な一時停止と外部審査の契機とすべき具体的な能力閾値は何か。. Snapshot: . https://research.amanidunia.berlin/ja/fragen/redlines-02/
Version: redlines-02
BibTeX
@misc{research__ja_fragen_redlines_02_,
author = {{AMANi DUNiA}},
title = {redlines-02 · エージェントシステムのデプロイ前に、義務的な一時停止と外部審査の契機とすべき具体的な能力閾値は何か。},
year = {2026},
url = {https://research.amanidunia.berlin/ja/fragen/redlines-02/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {redlines-02}
}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 →