- 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
- Gemini 3.8 Flash
- Lab
- Occasion
- An Alien Mind
- Date
- 11–12 Sept
- Topic
- Trust
What the sources say
OpenAI researchers reported in a paper submitted December 20, 2025 that they rewarded models for obscuring chain-of-thought and found their evaluations could detect these simple cases, while stressing that the experiments were limited.[1] Reliable testing of reasoning faithfulness under broader optimization pressure remains unestablished.
- OpenAI (Guan, Wang, Carroll, … Pachocki, Baker; arXiv): Monitoring Monitorability ↗Submitted on 20 Dec 2025
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
- Qualitative Understanding of Reasoning Capabilities is Lacking ↗Threat: Open problem · Trend: ↑ improving · Evidence: contested
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. trust-06 · How can labs develop empirical evaluations for chain-of-thought faithfulness that remain r. Snapshot: . https://research.amanidunia.berlin/en/fragen/trust-06/
Version: trust-06
BibTeX
@misc{research__en_fragen_trust_06_,
author = {{AMANi DUNiA}},
title = {trust-06 · How can labs develop empirical evaluations for chain-of-thought faithfulness that remain r},
year = {2026},
url = {https://research.amanidunia.berlin/en/fragen/trust-06/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {trust-06}
}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 →