Prompt EngineeringFazl Barez et al. (Oxford, Google DeepMind, Mila and others)University of OxfordGoogle DeepMind
Chain-of-Thought Is Not Explainability published
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Chain-of-Thought Is Not Explainability published — of 1,000 recent CoT papers, about 25% treat CoT as an interpretability technique
Why it matters
A position paper that makes the practice of using CoT as an explanation its subject
Source — Primary sources first; secondary reports are labelled “Press”
Officialaigi.ox.ac.ukhttps://aigi.ox.ac.uk/wp-content/uploads/2025/07/Cot_Is_Not_Explainability.pdfAdded in Week 35, 2026 · See that week
On the map — ① Prompt Engineering line
- Previous stopGPT-4.1
- This recordChain-of-Thought Is Not Explainability published
- Next stopChain-of-Thought Hijacking published