ainewsblitz.com

Breaking

OpenAI Pauses Reinforcement Learning on Latest Models for Two Weeks After Astra Cyber Review

  • Foundation Models
  • Security
  • AI Agents

OpenAI said it temporarily paused reinforcement learning (RL) training on its latest models intended for deployment for two weeks while it hardened and red-teamed its research environments and expanded monitoring coverage, and that its largest planned frontier RL run remains on hold. Smaller-scale training and evaluations are continuing, the company said, as it validates those safeguards and gathers more evidence of alignment.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,575 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year