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

The fact that you can train jointly, in fact, it's going to be the same on that.

You control how both the policy part and the guardrail part are trained.

Like the scenario of a completely adversarial case is hopeless.

There's always going to be a way to bypass whatever imperfect guardrail, and you're never going to have a completely perfect guardrail, right?

But if you control both sides,

In other words, you train both sides.

It's not like some evil person is building an agent that's going to defeat your guardrail.

No, you train the agent and you can train it in such a way that it will not be trying to, it's not going to be over-optimized in places where the guardrail is uncertain.

So you always make sure that the uncertainty, like the level of error of the guardrail is not gonna be like exploited by the policy part.

It's the same neural net, but different kinds of questions, right?

So the policy part is about probability of actions and the guardrail is probability of harm.

What do you mean by policy here?

Oh, some other machine learning system

that is agentic, in other words, goal-seeking.

And if it's trained by reinforcement learning and it somehow is trained to anticipate how the guardrail would respond, and maybe it gets some data about the answers that the guardrail gave in the past, when did the guardrail reject something, right?

So then it might be able to find a loophole in the guardrail.

But if you control both sides, then you can avoid this problem.

You don't actually need to have hard guarantees on the uncertainty estimator.

So I have a recipe to train the uncertainty prediction, but actually you don't formally need it.

It's just going to help your chances.

Showing 161–180 of 2,216 · page 9 of 111