Overview
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.
Source
Originally published at www.wired.com.
Technology
OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
Key Takeaway
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.
Frequently Asked Questions
What is "OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue" about?+
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.
Who reported this story?+
This story was reported by Wired.