Quartz·1 min read·medium

OpenAI paused work on its Astra model after it warned the AI might be capable of autonomous cyberattacks

Cris Tolomia
AI Summary

OpenAI has temporarily halted development on its Astra model following internal safety evaluations. The model was flagged for potentially reaching a critical threshold regarding autonomous cyberattack capabilities.

Preliminary evaluations found the unreleased model may have reached a "critical" cybersecurity threshold under the company's safety framework

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyaibusiness

Get the full story

Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.

Create free account

Already have an account? Sign in