How to pronounce“explainability”in English

Explainability is a huge one.

- Explainability is really interesting.

The kind of explainability that I was addressing earlier isn't consumer systems.

the definition and the explainability of the incentives was um decentralized such that no nobody can manipulate it

rather than just about explainability and then i think uh explanations are one tool that you use towards those goals

in terms of black neural network explainability.

So what I'm talking about explainability in is.

If you make good progress in explainability, now the system itself can engage in self-improvement much easier, increasing capability greatly.

you've uh forcing the explainability issue

explainable i think there are settings where explainability matters and these might these are these might be

And then we solve the entire problem of explainability because it's not hard to explain.

outside of the broader landscape of establishing trust and explainability at more of an individual level

It's not the holy grail of AI explainability, but at least, it explains something to the user beyond what they know.

they're building products with AI from an explainability perspective, from an accountability perspective.

exactly and the llp front and also just explainability of ai it's fascinating just a very question stephen wolfram looked at this with the

acknowledge is that so so so so i in that sense explainability and interpretability may matter

But I think it needs to develop under conditions of trust and under conditions of explainability.

Yeah, that explainability issue does come up even in your book a few times with respect to games.

itself about what it did well that's what humans do right I mean you talk about uh like Network explainability right and we give noral Nets a hard time

essentially break down how data is being collected, what kinds of decision making is this going on-- I'm not saying that you solve the explainability problem

Even small things like that in the design, little cues, that is explainability of a very practical type, you know?

So if you look at the president's executive order on artificial intelligence, there's a lot of really good constructs in there around explainability,

Because if we want to design a new bill of digital rights, we'll have to agree on things like fairness, transparency, openness, explainability.

I think, yes, there's an enormous amount of interest in explainability, interpretability.

Well, you have to bring it to the world and be clear about its purpose, its transparency, and its explainability.

You clear on your purpose, you'd be clear on transparency, you'd be clear on explainability, and then you have to live by things like, you own your data, I don't own your data.