Yoshua Bengio

speaker

2,216 appearances 5 recordings 5 series first heard Oct 2018 last heard 7 May

Yoshua Bengio’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 — 3 in all, peaking in May 2026 with 1.

Appearances

newest first · ▶ plays the moment

80,000 Hours Podcast · #243 – 'Godfather of AI' Yoshua Bengio: "I now see a path" to safe superintelligent AI · 7 May 2026 podcast

It's also trained to be internally coherent.

Those explanations have to be coherent with each other.

So the way in which it could fail is by basically feeling it doesn't have enough confidence about a question.

So it could just start answering, I don't know, all the time?

Yeah, but yes.

Now, you have to understand it's not actually saying, I don't know.

It's producing a number between zero and one that is a probability that something is true.

And in fact, it's also producing a confidence interval around that number.

And so, yeah, it could be that in some domains, there's just not enough information in the data that it has seen, or maybe it wasn't trained long enough to deduce good theories about that domain.

And at the end of the day, as a consequence, it's going to answer with a probability that is far from zero and one, like far from full confidence.

But that's what we want.

Like we want that kind of epistemic humility and honesty, because when it gets to like really serious safety questions, we'd rather have something that says, I don't know when it's the real thing is it doesn't know, then the sort of thing we currently see with frontier models is often they will have excessive confidence in their answers.

I don't think that they really understand what I'm doing.

And to their credit, I haven't put out the math yet.

So there's another factor that may be at play here based on the discussions I've had with people inside the leading companies, which is their

so focused on short-term survival, as in continuing to compete, that they put all of their attention, the code red sort of thing, into small incremental changes to the current recipe.

considering a different recipe would be an investment, not just in money, but in people and like code that right now they could do it, like they have the money to do it.

It's more like a mental focus, I think, that is going on here that comes not because of badwill, but because of that competition that is very, very fierce between the companies.

I think what you're saying is plausible.

I actually think there's a related possibility, which goes maybe more to policy questions.

Showing 681–700 of 2,216 · page 35 of 111