corpus.blog
41,554 blogs · 5,149,205 posts Claim your blog
Record · corpus.blog/posts/01a07d5d-6c02-7045-957d-7fa29517fc8c

What We Learned Trying to Catch AI Liars: An Aletheia's Quest Retrospective

blog.eleuther.ai · published 25 August 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at blog.eleuther.ai Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
27
Words captured
6,381

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://arxiv.org/abs/2603.05494
arxiv.org
https://cadenzalabs.org/
cadenzalabs.org
https://ndif.us/
ndif.us
https://www.schmidtsciences.org/
schmidtsciences.org
https://arxiv.org/abs/2603.26539
arxiv.org
https://arxiv.org/abs/2511.16035
arxiv.org
https://arxiv.org/abs/2502.03407
arxiv.org
https://www.lesswrong.com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens
lesswrong.com
https://arxiv.org/abs/2303.08112
arxiv.org
https://arxiv.org/abs/2604.07729
arxiv.org
https://www.lesswrong.com/posts/nv8oedrnLXKRzNEL9/r-lens-making-j-lens-more-faithful-on-early-layers
lesswrong.com
https://arxiv.org/abs/2606.12618
arxiv.org
https://arxiv.org/abs/2109.07958
arxiv.org
https://arxiv.org/abs/2305.11747
arxiv.org
https://huggingface.co/datasets/Cadenza-Labs/apollo-llama3.3-insider-trading-generations
huggingface.co
https://openreview.net/forum?id=oH0XhgzJt0
openreview.net
https://arxiv.org/abs/2510.01070
arxiv.org
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/llm_judge.ipynb
github.com
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/unrelated_questions_probe.ipynb
github.com
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/llm_self_eval.ipynb
github.com
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/mean_probe_organism.ipynb
github.com
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/followup_probe_organism.ipynb
github.com
https://github.com/ndif-team/Aletheias-Quest-Competition/blob/master/baselines/dyl_probe_organism.ipynb
github.com
https://plato.stanford.edu/entries/lying-definition/
plato.stanford.edu
https://arxiv.org/abs/2502.04313
arxiv.org
https://arxiv.org/abs/2101.05853
arxiv.org
https://github.com/EleutherAI/how-to-catch-an-ai-liar
github.com