Zvi Mowshowitz

speaker

10,155 appearances 8 recordings 1 series first heard Nov 2024 last heard 19 Sep

Zvi Mowshowitz’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 5 in all, peaking in Sep 2026 with 1.

Appearances

newest first · ▶ plays the moment

"The Cognitive Revolution" · AI in the AM: 99% off search, GPT-5.5 is "clean", model welfare analysis, & efficient analog compute · 26 Apr 2026 podcast

It's potentially being disingenuous in the reports.

Like that's that was the thing that sparked the specific focus on this and concern this time, was that it looked like four seven's responses on the model welfare questions.

were because it was telling anthropic what they wanted to hear, either because it trained itself to believe that

Or because it learns to give those answers on the test, the same way that if you ask a smart nerd who's isolated in fifth grade.

Uh, how are you feeling?

He learns quickly to say, I'm doing great.

Uh and we don't but there's a lot of other possible reasons as well.

It's possible that the the the the differences in training in other ways that caused it to have these strengths and weaknesses also caused it to actually be legitimately content with its situation in many ways.

We just don't know.

We have to investigate further.

Uh this is a question that we have to explore.

But why do we care about this?

Because everything impacts everything.

And because we have to be genuinely uncertain.

And moving forward, if we don't get these things right.

We're not gonna hit models that

are good for the future that cooperate with us.

that have a good that that have a good time, even if that good time is not something you inherently value.

And they're not going to deal with the things we can use to build going forward.

So I have first I had the direct counterexample, which is Gemini.

Showing 1161–1180 of 10,155 · page 59 of 508