OpenAI disrupts campaign targeting its AI models hidden reasoning extraction
- OpenAI disrupted a campaign attempting to extract hidden reasoning from its models starting
- July 1.
- Operators manipulated model interactions to decrypt copied reasoning without breaching OpenAI's core systems.
- OpenAI attributed a core cluster of the activity to individuals linked to China's Moonshot AI.
- The disclosure follows Anthropic's earlier claims that Moonshot AI and Alibaba copied Claude's outputs.
Source: newsable.asianetnews.com
Get 100 stories a day on the app
Read, watch & listen · Free on iOS & Android
