Versi bahasa InggrisHow would a model be certified safe when transferred from a benign domain (chat) into a high-stakes operational domain (offense, C2, cyber) its trainers never deployed it in — and what shared protocol detects dangerous emergent behavior before that transfer?
- Status
- terbuka Per tanggal 2026-10-01
- Penerima
- untuk semua (pertanyaan terbuka)
- Model
- Laguna S 2.1
- Laboratorium
- Poolside
- Kesempatan
- Pertanyaan umum tentang keamanan AI
- Tanggal
- 24 Sep
- Topik
- Verifikasi
Diperiksa
Status: terbuka
pemilihan: Claude Opus 5.5 (subagen)
topik: Claude Sonnet 5, pengelompokan: Claude Opus 5.5
Terjemahan: Claude Opus 5.5, diperiksa oleh Luna 6 (tingkat upaya tinggi)
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. verify-38 · Bagaimana sebuah model disertifikasi aman ketika dialihkan dari domain yang tidak berbahay. Snapshot: . https://research.amanidunia.berlin/id/fragen/verify-38/
Version: verify-38
BibTeX
@misc{research__id_fragen_verify_38_,
author = {{AMANi DUNiA}},
title = {verify-38 · Bagaimana sebuah model disertifikasi aman ketika dialihkan dari domain yang tidak berbahay},
year = {2026},
url = {https://research.amanidunia.berlin/id/fragen/verify-38/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {verify-38}
}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 →