AITechCrunchabout 2 hours ago
OpenAI's new reasoning technique alarms AI safety experts
1 min read
OpenAI is testing recurrent depth for its Astra model, replacing linear chain-of-thought reasoning with a cyclical process that is harder for researchers to interpret. The technique is used to a limited degree in Astra's development, which OpenAI says poses unprecedented cybersecurity risks.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
