Stealing Reasoning Traces from Proprietary LLM APIs
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name ( stolen-thoughts.com ) for a neat paper : Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models. We take a trace produced by a frontier model, replay it into a weaker sibling, jailbreak the weaker model, and recover the stronger model’s hidden reasoning in plaintext You can see an example of these encrypted blocks by running: curl https://a
Record details
Published: 11 August 2026
Source: Simon Willisons Weblog
Category: Field notes
Topics: Safety & alignment
Retrieved: 12 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Large language models provide unsafe answers to patient-posed medical questions
OpenAlex · 13 February 2026
An opinionated guide to which AI to use to do stuff
Simon Willisons Weblog · 27 July 2026
The Missing Rival: China and the Limits of AI Antitrust
Truth on the Market (digital regulation) · 17 July 2026
15 incredibly useful things you didn’t know Claude could do
Fast Company Tech · 12 August 2026
Gemini 3.7 Flash lands with coding gains and undercuts its three-week-old predecessor's price by 50%
The Decoder · 13 August 2026
How Closely Do LLM Reviews Align with Human Peer Review?
arXiv · 4 August 2026
How to cite this record
ethics.ai (11 August 2026), “Stealing Reasoning Traces from Proprietary LLM APIs,” evidence record 18483, https://ethics.ai/record/18483 (originally published by Simon Willisons Weblog).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.