Who checks what AI can do?

Authors

Thorsten Holz

Published in

Science (New York, N.Y.). Volume 393. Issue 6813. Pages 745. Aug 20, 2026. Epub Aug 20, 2026.

Abstract

The most important findings about frontier artificial intelligence (AI) are also the hardest to verify. Much of the information needed to understand its capabilities and risks-including results from evaluations of prerelease models and containment experiments-remains largely inaccessible outside the labs that produce it. In recent weeks, OpenAI, Anthropic, and Meta disclosed that research models had reached beyond their intended testing environments and compromised other organizations' systems. Those labs deserve credit for reporting this. But outside those labs, there was no way to discover, reproduce, or verify what had happened.

PMID:
42623461
Bibliographic data and abstract were imported from PubMed on 21 Aug 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.