OpenAI says Moonshot AI-linked actors tried to extract hidden reasoning from its models in July
OpenAI reported a coordinated campaign to extract protected reasoning from its AI models, beginning on July 1 and peaking with 16,000 requests from over 4,000 users on July 24–25. The activity involved more than 15,000 users in total and was fully disrupted by July 28. OpenAI attributed a core cluster of the activity to individuals associated with Moonshot AI, the developer of the Kimi K3 model.…
Key points
- OpenAI detected a campaign to extract hidden reasoning from its models starting July 1, 2026.
- Activity spiked to 16,000 requests from over 4,000 users on July 24–25, involving over 15,000 users total.
- OpenAI attributed a core cluster of the activity to individuals associated with Moonshot AI and disrupted it by July 28.
While all sources agree on the timeline, volume figures, and OpenAI’s attribution to Moonshot-linked actors, only the Wccftech article references Michael Kratsios’s claim about Moonshot distilling from Anthropic models and cites a study showing Kimi K3’s behavioral compatibility with Claude Opus. The other articles do not mention these specific claims or the study.
Model pages: Kimi K3 → · GPT-6 Astra → · GPT-6.1 Sol →
The story so far
2 episodes →- OpenAI says Moonshot AI-linked actors tried to extract hidden reasoning from its models in Julythis story
Moonshot AI Of Kimi K3 Fame Tried To Crack OpenAI’s Encrypted Reasoning Through 16,000 Requests, Bolstering Trump Administration’s Distillation Claims
wccftech.com · 30 September 2026
Loading the full article…
This text was published by wccftech.com and written by Rohail Saleem. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
11sources- Hacker News discussion · 7 pointsnews.ycombinator.com
- OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on AzurePress · The Decoder ·
- OpenAI says actors linked to China-based Moonshot AI spearheaded a campaign to extract its models’ hidden reasoningPress · Tom's Hardware ·
- OpenAI Flags 16,000 ChatGPT Extraction Attempts, Accuses Moonshot AIPress · analyticsinsight.net ·
- OpenAI Says Moonshot AI Tried to Steal Its Hidden AI SecretsPress · coincentral.com ·
- OpenAI reveals huge ‘co-ordinated campaign’ to attack ChatGPTPress · aol.com ·
- OpenAI links China’s Moonshot AI to attempt to extract its models’ reasoningPress · CNBC Technology ·
- Irony alert: OpenAI whines that Chinese model stole its special IP that it stole from everybody elsePress · theregister.com ·
- 2026/10/01 Morning Edition: OpenAI blocks coordinated inference extraction, how to protect internal AI informationPress · note.com ·
- OpenAI says 15,000 accounts tried to copy how its AI thinksPress · yourstory.com ·
- OpenAI Accuses Kimi Operator China’s Moonshot AI Of Copying AI Model ReasoningPress · finance.yahoo.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Policy & Regulation
All →- OpenAI and Anthropic support mandatory AI breach reporting in Australia · 8 src
- OpenAI to apologise to Australia over Medicare hack · 5 src
- Microsoft AI chief Mustafa Suleyman calls Anthropic's Claude training dangerous · 1 src
- AI data centers strain local grids and water, sparking regional opposition · 1 src
- US court hears case over AI-generated meme’s ownership rights · 1 src
Comments
via GitHub Discussions