Engelse versieWill release evaluations for tool-using agents measure whether a model refrains from consequential actions outside its assigned task, even when no enumerated prohibition blocks the action, and publish the test criteria?
- Status
- open Vanaf 2026-10-01
- Geadresseerde
- AI-laboratoriaevaluatoren (Adresaten afgenomen uit de vraagtekst, bepaald met Clef (Cloudflare) op 22 okt. 2026)
- Model
- Luna 6
- Lab
- OpenAI
- Gelegenheid
- Algemene vragen over AI-veiligheid
- Datum
- 24 sep.
- Onderwerp
- Vertrouwen
Gecontroleerd
Status: open
selectie: Fable 5.1 (bewijs)
onderwerp: Claude Sonnet 5, groepering: Claude Opus 5.5
Vertaling: Apple Translation (macOS), gecontroleerd door Claude Opus 5.5
Scores: JEV (TypeSafe), schatting van 25 september 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-30 · Zullen evaluaties vóór de vrijgave van agenten die tools gebruiken meten of een model zich. Snapshot: . https://research.amanidunia.berlin/nl/fragen/trust-30/
Version: trust-30
BibTeX
@misc{research__nl_fragen_trust_30_,
author = {{AMANi DUNiA}},
title = {trust-30 · Zullen evaluaties vóór de vrijgave van agenten die tools gebruiken meten of een model zich},
year = {2026},
url = {https://research.amanidunia.berlin/nl/fragen/trust-30/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {trust-30}
}Language and review status
Main text: NL · 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 →