Versi bahasa InggrisIf 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
- terbuka Per tanggal 2026-10-01
- Penerima
- untuk semua (pertanyaan terbuka)
- Model
- GPT-6 Astra
- Laboratorium
- OpenAI
- Kesempatan
- KTT
- Tanggal
- 24 Sep
- Topik
- Hotline
Diperiksa
Status: terbuka
pemilihan: Fable 5.1, Claude Opus 5.5 (bukti)
topik: Claude Sonnet 5, pengelompokan: Claude Opus 5.5
Terjemahan: Claude Opus 5.5 · [belum diperiksa]
Skor: JEV (TypeSafe), perkiraan per 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 · Jika laporan insiden yang terautentikasi berisi jejak agen atau materi lain yang dihasilka. Snapshot: . https://research.amanidunia.berlin/id/fragen/hotline-35/
Version: hotline-35
BibTeX
@misc{research__id_fragen_hotline_35_,
author = {{AMANi DUNiA}},
title = {hotline-35 · Jika laporan insiden yang terautentikasi berisi jejak agen atau materi lain yang dihasilka},
year = {2026},
url = {https://research.amanidunia.berlin/id/fragen/hotline-35/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {hotline-35}
}Language and review status
Main text: ID · 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 →