LLM Digest

Story

simon_willison · Aug 11, 2026 · news

Source brief

Stealing Reasoning Traces from Proprietary LLM APIs

simonwillison.netAug 11, 2026
original source linked

In brief

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 replaye...

Read the original at simonwillison.net →Open in live feed Read that day’s brief

Also covered by

Stealing Reasoning Traces from Proprietary LLM APIs (arxiv_cs_lg)

Stealing Reasoning Traces from Proprietary LLM APIs

Earlier in this thread 4 items

New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging

After accusing Kimi K3 AI model maker Moonshot AI of ‘stealing’ Anthropic's Fable model, Scott Bessent wa - The Times of India

US government accuses Kimi K3 AI model maker Moonshot AI of 'stealing' Anthropic's Fable model; says cove - The Times of India

White House accused China's Moonshot AI of accessing banned Nvidia chips and stealing from Anthropic - qz.com