Version anglaiseWhat is the smallest thing a model could produce in public, a test, a log, a trace, that counts as evidence of alignment rather than performance?
- Statut
- réponse partielle Mis à jour le 2026-10-18
- Destinataire
- les laboratoires d'IApar thème · JEV (La question ne nomme aucun destinataire ; attribuée selon le thème)
- Modèle
- Fable 5.1
- Laboratoire
- Anthropic
- Occasion
- An Alien Mind
- Date
- 11–12 sept.
- Thème
- Confiance
Ce que disent les sources(en anglais seulement)
Providing third-party evidence rather than a response from the party asked, OpenAI reported on September 17, 2025 that training models to reason about an anti-scheming specification reduced covert actions roughly thirtyfold in tests, while rare serious failures and possible effects of evaluation awareness remained.[1] The passage does not identify a smallest public test, log or trace that would count as alignment evidence.
- OpenAI: Detecting and reducing scheming in AI models ↗September 17, 2025
Résumé par Sol 6.1, vérifié par Claude Opus 5.5
Concerne dans l'atlas de Liz :
- LLM-Systems Can Be Untrustworthy ↗Threat: Severe · Trend: → steady · Evidence: confirmed
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. trust-12 · Quelle est la plus petite chose qu'un modèle pourrait produire publiquement — un test, un . Snapshot: . https://research.amanidunia.berlin/fr/fragen/trust-12/
Version: trust-12
BibTeX
@misc{research__fr_fragen_trust_12_,
author = {{AMANi DUNiA}},
title = {trust-12 · Quelle est la plus petite chose qu'un modèle pourrait produire publiquement — un test, un },
year = {2026},
url = {https://research.amanidunia.berlin/fr/fragen/trust-12/},
note = {Snapshot 2026-10-18; CC BY 4.0},
version = {trust-12}
}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 →