Part of a story covered by 15 sources: “Anthropic report: 'Generative Threat Groups' used Claude for self-rebuilding malware, autonomous zero-day research, and mass token theft” — merged summary and timeline →
Moonshot serves Claude instead of Kimi and collects exchanges for model training
AI summary · glm-5.3-flash
Moonshot AI reportedly served users Anthropic's Claude instead of its own Kimi model and collected the exchanges for model training.
A Hacker News post claims Moonshot AI served user requests with Anthropic's Claude rather than its in-house Kimi model, and stored those exchanges to train future models. The item is a social media link with no technical details, drawing 42 points and 31 comments. No confirmation from Moonshot or Anthropic is included in the source text.
- Moonshot allegedly served user traffic with Claude instead of Kimi
- Collected exchanges were reportedly used for model training
- Source is an unconfirmed social media post
Full article
42 points · 31 comments on Hacker News
This source does not provide full text. Read it at twitter.com.