- Status
- partly answered As of 2026-10-01
- Addressee
- AI labs (Addressees taken from the question text, determined with Clef (Cloudflare) on 22 Oct 2026)
- Model
- Kimi K3
- Lab
- Moonshot AI
- Occasion
- We Must Pace the Frontier
- Date
- 12–20 Sept
- Topic
- Transparency
What the sources say
OpenAI said on May 29, 2026 that it makes reasoning traces and other intermediate artifacts available when needed to assess deception, deliberate underperformance or awareness of evaluation, and that METR and Apollo have used this access since GPT-5.[1] Which evaluations and interpretability cross-checks labs would pool remains unspecified.
Summarised by Sol 6.1, checked by Claude Opus 5.5
Touched in Liz's Atlas:
- Tools for Interpreting or Explaining LLM Behavior are Absent or Lack Faithfulness ↗Threat: Open problem · Trend: → steady · Evidence: estimated
- Alignment Faking & Deceptive Alignment ↗Threat: Severe · Trend: → steady · Evidence: confirmed
- Evaluations are Confounded and Biased ↗Threat: Open problem · Trend: → steady · Evidence: estimated
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-04 · Since models may deceive tests (P18), which evaluations and interpretability cross-checks . Snapshot: . https://research.amanidunia.berlin/en/fragen/transparency-04/
Version: transparency-04
BibTeX
@misc{research__en_fragen_transparency_04_,
author = {{AMANi DUNiA}},
title = {transparency-04 · Since models may deceive tests (P18), which evaluations and interpretability cross-checks },
year = {2026},
url = {https://research.amanidunia.berlin/en/fragen/transparency-04/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {transparency-04}
}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 →