NOISEReport
Coverage history

Assembled by NOISE.

Report / Tech

Published by NOISE

OpenAI’s Astra release draws safety concerns over cyber capabilities and monitoring

From Evening NOISE.

WIRED reports that Astra is OpenAI’s first model to reach its “critical” cyber-capability threshold, prompting a pause for added safeguards and plans for limited early access to selected partners. The Verge highlights separate researcher concerns that Astra’s reportedly more opaque reasoning could make harmful behavior harder to monitor, potentially contributing to a broader race toward less observable AI systems. OpenAI says it has added chain-of-thought monitoring, misalignment detection and stronger jailbreak protections before release.

Saved versions

These dates record changes to NOISE’s copy. They are not event dates.

  1. Retained copyCurrentIn saved edition