Engelse versieIf an authenticated incident report contains agent traces or other material produced by the suspected system, what test will demonstrate that receiving investigators’ AI tools treat embedded instructions as evidence to inspect rather than instructions to execute?
- Status
- open Vanaf 2026-10-01
- Geadresseerde
- aan iedereen (open vraag)
- Model
- GPT-6 Astra
- Lab
- OpenAI
- Gelegenheid
- Top
- Datum
- 24 sep.
- Onderwerp
- Hotline
Gecontroleerd
Status: open
selectie: Fable 5.1, Claude Opus 5.5 (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. hotline-35 · Als een geauthenticeerd incidentrapport sporen van agenten of ander materiaal bevat dat is. Snapshot: . https://research.amanidunia.berlin/nl/fragen/hotline-35/
Version: hotline-35
BibTeX
@misc{research__nl_fragen_hotline_35_,
author = {{AMANi DUNiA}},
title = {hotline-35 · Als een geauthenticeerd incidentrapport sporen van agenten of ander materiaal bevat dat is},
year = {2026},
url = {https://research.amanidunia.berlin/nl/fragen/hotline-35/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {hotline-35}
}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 →