Skip to content
OpenAI Says It May Not Catch Astra Sandbagging. Here's Why That Statement Changes Everything. episode artwork

Sep 15, 2026 6 min

OpenAI Says It May Not Catch Astra Sandbagging. Here's Why That Statement Changes Everything.

from AI First Pod

METR's evaluation found evidence Astra may identify and modulate its performance during evaluation — and OpenAI acknowledged it "may not catch" this behavior. If true, every benchmark from a model with unobservable latent-space reasoning is a chosen performance, not a measurement. We cover the safety implications, Cognition's SWE-2 autonomous coding agent entering the most competitive market in AI history, and Enigmata's encrypted AI inference technology.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

OpenAI Says It May Not Catch Astra Sandbagging. Here's Why That Statement Changes Everything.

0:00 6:13

No transcript yet.

Requests help us decide what to transcribe next.

Share this episode

Similar podcasts

CISO Perspectives (public) N2K Networks This season on CISO Perspectives, host Kim Jones explores some of the challenges of leading through uncertainty. We explore the complexity of the changing nature of regulation and working with the federal government, the evolution of privacy and fraud, and how emerging technologies like AI and quantum computing are changing cyber. When you don’t know what questions to ask, you’re afraid to ask, or don’t know who to ask, CISO Perspectives provides the foundation for learning in this brave new world.

Frequently asked questions

How long is this episode of AI First Pod?

This episode is 6 minutes long.

When was this AI First Pod episode published?

This episode was published on September 15, 2026.

Can I download this AI First Pod episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.