Elon Musk

That's right.

People say, what if the AI tricks us and introduces us?

Actually, other humans are doing that to other humans all the time.

Well, you're pointing out that propaganda is constant.

Every day another PSYOP, you know.

Today's PSYOP will be like Sesame Street PSYOP of the day.

I do think you want to actually have very good ways to look inside the mind of the AI.

So this is one of the things we're working on.

And Anthropic's done a good job of this, actually, being able to look inside the mind of the AI.

So effectively developing debuggers that allow you to trace to a very fine-grained level, to effectively to the neuron level if you need to.

And then say, OK, it made a mistake here.

Why did it do something that it shouldn't have done?

And did that come from bad pre-training data?

Was it some mid-training, post-training, fine-tuning, some RL error?

There's something wrong with that.

It did something where maybe it tried to be deceptive, but most of the time, it just did something wrong.

It's a bug, effectively.

So developing really good debuggers for seeing where the thought, the thinking went wrong and being able to trace the origin of the wrong thing, of where it made the incorrect thought or potentially where it tried to be deceptive is actually very important.

We have several hundred people who... I mean, I prefer the word engineer more than I prefer the word researcher.

Mm-hmm.