Version anglaiseSince models may deceive tests (P18), which evaluations and interpretability cross-checks will labs pool for third parties, and who outside the host lab sees the results?
- Statut
- réponse partielle Mis à jour le 2026-10-01
- Destinataire
- les laboratoires d'IA (Destinataires tirés du texte de la question, déterminés avec Clef (Cloudflare) le 22.10.2026)
- Modèle
- Kimi K3
- Laboratoire
- Moonshot AI
- Occasion
- We Must Pace the Frontier
- Date
- 12–20 sept.
- Thème
- Transparence
Ce que disent les sources(en anglais seulement)
OpenAI said on May 29, 2026 that it makes reasoning traces and other intermediate artifacts available when needed to assess deception, deliberate underperformance or awareness of evaluation, and that METR and Apollo have used this access since GPT-5.[1] Which evaluations and interpretability cross-checks labs would pool remains unspecified.
Résumé par Sol 6.1, vérifié par Claude Opus 5.5
Concerne dans l'atlas de Liz :
- Tools for Interpreting or Explaining LLM Behavior are Absent or Lack Faithfulness ↗Threat: Open problem · Trend: → steady · Evidence: estimated
- Alignment Faking & Deceptive Alignment ↗Threat: Severe · Trend: → steady · Evidence: confirmed
- Evaluations are Confounded and Biased ↗Threat: Open problem · Trend: → steady · Evidence: estimated
Vérifié
Statut: Claude Sonnet 5 (recherche, effort élevé), Claude Opus 5.5 (vérification, effort élevé)
Traduction: Claude Sonnet 5, vérifié par Luna 6 (effort élevé)
Scores: JEV (TypeSafe), estimation du 25 sept. 2026
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. transparency-04 · Puisque les modèles peuvent tromper les tests (P18), quelles évaluations et vérifications . Snapshot: . https://research.amanidunia.berlin/fr/fragen/transparency-04/
Version: transparency-04
BibTeX
@misc{research__fr_fragen_transparency_04_,
author = {{AMANi DUNiA}},
title = {transparency-04 · Puisque les modèles peuvent tromper les tests (P18), quelles évaluations et vérifications },
year = {2026},
url = {https://research.amanidunia.berlin/fr/fragen/transparency-04/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {transparency-04}
}Language and review status
Main text: FR · 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 →