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 monthsRecordings per month over the last 12 months — 2 in all, peaking in Jun 2026 with 1.
Appearances
would behave cautiously.
It'll do things when it's sure that that's what we want.
It will ask permission.
It will defer to human feedback.
And we can prove, actually, that it will allow itself to be switched off, which is really important if you're worried about humans losing control.
Here is a kind of AI system where we can prove mathematically that it wants to be switched off if we want to switch it off.
And the reason is obvious, right?
Why would we switch it off?
Because it's doing something we don't like.
Like its constitution, it doesn't want to do things that we don't like, but it doesn't know what they are, so it could make a mistake.
If it's making a mistake, it wants to be corrected.
It wants to be switched off to avoid doing the thing that we don't like.
This approach is, I think, promising.
There's a lot of work still to be done.
Meanwhile,
Out in the real world, things are actually taking an even worse direction because the companies have abandoned the standard model where the objective is specified and the AI system is sort of constitutionally obliged to just maximize the objective.
And instead, what we're building is this, in some sense, imitation human.
And let me be explicit about why I'm saying that.
So the training method is to collect lots of examples of humans making decisions.
In the case at hand, the decisions that human makes are what word to put next into a document.
Showing 161–180 of 1,902 · page 9 of 96
← Previous
Next →