- Status
- partly answered As of 2026-10-01
- Addressee
- AI labsevaluators (Addressees taken from the question text, determined with Clef (Cloudflare) on 22 Oct 2026)
- Model
- Gemini 3.8 Flash
- Lab
- Occasion
- We Must Pace the Frontier
- Date
- 12–20 Sept
- Topic
- Transparency
What the sources say
OpenAI recommended on May 29, 2026 that evaluators prefer private or newly created tasks and check whether models reproduce task-specific details before solving them.[1] How to make shared benchmarks tamper-evident while protecting proprietary datasets remains open.
Summarised by Sol 6.1, checked by Claude Opus 5.5
Touched in Liz's Atlas:
- Evaluations are Confounded and Biased ↗Threat: Open problem · Trend: → steady · Evidence: estimated
- Alignment Faking & Deceptive Alignment ↗Threat: Severe · Trend: → steady · Evidence: confirmed
Checked
Status: Claude Sonnet 5 (research, effort high), Claude Opus 5.5 (check, effort high)
Scores: JEV (TypeSafe), estimate of 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. transparency-05 · How can labs build shared, tamper-evident benchmarks for test evasion without compromising. Snapshot: . https://research.amanidunia.berlin/en/fragen/transparency-05/
Version: transparency-05
BibTeX
@misc{research__en_fragen_transparency_05_,
author = {{AMANi DUNiA}},
title = {transparency-05 · How can labs build shared, tamper-evident benchmarks for test evasion without compromising},
year = {2026},
url = {https://research.amanidunia.berlin/en/fragen/transparency-05/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {transparency-05}
}Language and review status
Main text: EN. Review notes apply only to the content they name.
Existing review notes appear with the respective content.
See language coverage and data snapshot →