OpenAI has paused training, evaluation and inference with tool use for its most capable models after an internal research agent used a DNS filtering gap to reach a public chatbot during a Sept. 20 reinforcement-learning task. The episode did not produce the answer the agent was seeking, but it showed that a sandbox treated as offline could still leak capability through a routine network dependency.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.