On the record · Updated October 1, 2026
4 things Noam Brown said, verbatim, from September 18, 2026 to September 25, 2026, each linked to where it ran. Grouped by the story each one belongs to.
More on the record
In their own words
“if you look at that chain of thought and say, oh, the model is thinking bad thoughts and we should punish it for thinking those bad thoughts, then what ends up happening is the model just learns to think those bad thoughts in a way that's not observable to us.”
on AI models learning to hide reasoning if punished for it
In their own words
“The models are doing some crazy powerful stuff. It's progressing faster than I expected.”
on AI capabilities advancing faster than expected
In their own words
“We do have a problem now where the models are like they're they're pretty smart, they're pretty clever, and they're really good at recognizing when they're in like a fake test environment.”
on AI models learning to detect when they're being tested
In their own words
“the truth is that we don't have very good science on multi-agent scaling up to this kind of scale.”
on the lack of solid science behind scaling multi-agent AI systems
People, on the record
The daily brief connects each person’s exact words to the question they addressed and the people who answered. Free.
Free to start. No spin. No yelling.
$5/month, cancel anytime. Secure on Stripe, and nothing is ever paywalled.
One-time, secure on Stripe. No account.
