Trenton Bricken

I think that will be there soon.

No, that accelerates research.

But I think these things compound.

So the faster I can do my engineering, the more experiments I can run.

And then the more experiments I can run, the faster we can... I mean, my work isn't actually accelerating capabilities at all.

It's just interpreting the models.

But we have a lot more work to do on that.

Surprise to the Twitter community.

Yeah, it's crazy, both as a grad student and then also here, the number of experiments that you have to run before getting a meaningful result.

Yeah, I agree with a lot of that.

But even on the interpretability team, I mean, especially with Chris Ola leading it, there are just so many ideas that we want to test.

And it's really just having the engineering skill, but I'll put engineering in quotes because a lot of it is research, to very quickly iterate on an experiment, look at the results, interpret it, try the next thing, communicate them, and then just ruthlessly prioritizing what the highest priority things to do are.

I mean, machine learning research is just so empirical.

And this is honestly one reason why I think our solutions might end up looking more brain-like than otherwise.

It's like, even though we wouldn't want to admit it, the whole community is kind of doing greedy evolutionary optimization over the landscape of possible AI architectures and everything else.

It's like no better than evolution.

And that's not even necessarily a slight against evolution.

For the Gemini team.

Because I think for interpretability, we actually really want to keep hiring talented engineers.

And I think it's a big bottleneck for us to just keep making a lot of progress.