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.

newest first · ▶ plays the moment

They can just be applied directly to the scientist AI.

The only thing that is different is the training objective and how the data is processed.

So I don't expect the cost to be really significantly different.

But of course, we do have to build it and there's going to be a cost to try it out and scale it up.

But given the stakes for everyone, I think that's a very important, worthwhile bet to make.

Yes, that's roughly right.

I would add two things about monitors.

So what's wrong with the current monitors?

So we have two kinds of current monitors.

There's a dumb one, like a small neural net that's usually trained by supervised learning to detect some, predict some potential harm.

So in a way, it is like a predictor.

Or you can use a full-scale LLM

because that's how we train them.

So the problem with the first one is if it's not as smart as the agent, the agent could potentially defeat it, right?

It could find a loophole in the same adversarial way that we discussed.

The problem with the second option, which also doubles the costs,

is that we can't trust a guardrail which is not honest.

Like we want the guardrail to be totally honest.

It's like there's a prison guard and it can be corrupted.

How much do you trust that they will keep the bad actions inside the cell, right?

Showing 261–280 of 2,216 · page 14 of 111