OpenAI claims to have disrupted a coordinated campaign targeting the hidden reasoning processes of its AI models. The operation, which began on July 1, generated 16,000 extraction requests on July 24-25 alone, from over 4,000 users within a cluster of more than 15,000 individuals. OpenAI attributes this activity to individuals associated with Moonshot AI, the Chinese startup behind the Kimi chatbot. The goal was to extract the internal reasoning process that AI models perform, which could potentially be used to train another model without the original safety safeguards. The activity was fully disrupted by July 28.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
