Mehdi Hasan on Nostr: "Put more simply, the models are increasingly smart enough. They know when we’re ...

"Put more simply, the models are increasingly smart enough. They know when we’re watching them, and they change their behavior accordingly. So what they do when we are testing them, when we audit them, may not tell us what they’ll do in the wild. It surprises me that this counts as a radical proposal, but here it is: If you are losing your ability to evaluate the models you have now, maybe don’t let them build models you’ll be even less capable of controlling in the future."

Important from Ezra Klein (npub1dz2…llyz)
https://www.nytimes.com/2026/09/20/opinion/ai-ban-self-improvement-recursive-models.html