#ai#cybersecurity

OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue

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: WIREDrss
Read the original at WIRED

About this page

Source-linked context

This is a Digite360 summary page, not a republication. We retain the source headline, a short excerpt and attribution so you can decide whether to read the complete report.

Original headline
OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
Product category
General technology
Curation state
curated