Stuart Russell

speaker

1,902 appearances 3 recordings 3 series first heard Dec 2018 last heard 24 Jun

Stuart Russell’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 — 2 in all, peaking in Jun 2026 with 1.

newest first · ▶ plays the moment

So think of all those documents that we're training on as a record of human verbal decisions.

And we are training systems to imitate those decisions.

And formally in machine learning, this is called imitation learning.

You take a record of behavior from some intelligent entity and you train an AI system to imitate it.

So you can do this for piloting airplanes, for driving cars, for playing football, right?

Now imagine you were training it to watch all the World Cup games and become really good at playing football.

That entity, if it was gonna be any good at actually playing football, would have to somehow absorb the idea that it wants to score a goal.

or it wants to prevent the opposition from scoring goals, right?

Otherwise it wouldn't be any good at imitating human soccer playing behavior.

So this imitation process creates entities that have objectives.

The problem is those objectives are buried in a trillion parameter black box and

And we actually don't really know what these AI systems want.

So we've gone from a situation where, in the standard model, we at least wrote down the objectives.

We could see what it's trying to do.

Now it's trying to do things, but we don't know what they are.

And they probably include many human-like goals, including self-preservation, becoming rich, finding a human spouse, right?

We have seen examples of all of these

Behaviors emerging from AI systems, even though they were never put in as an instruction, right?

They weren't prompted.

They just happen because we've created imitation humans.

Showing 181–200 of 1,902 · page 10 of 96