Amanda Askell

speaker

338 appearances 1 recordings 1 series first heard Jan 2026 last heard 23 Jan

Amanda Askell’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 — 1 in all, peaking in Jan 2026 with 1.

Appearances

newest first · ▶ plays the moment

Hard Fork · Will ChatGPT Ads Change OpenAI? + Amanda Askell Explains Claude's New Constitution · 23 Jan 2026 podcast

Here's how we would like you to act and to be.

And here's like the reasons why we would like that.

And then the hope is like if you get a completely unanticipated situation, if you understand like the kind of values behind your behavior,

I think that that's going to generalize better than a set of rules.

So if you understand the reason you're doing this is because you actually are trying to care about people's well-being and you come to a new situation where there's hard conflicts between someone's well-being and what their stated preferences are, you're a little bit better equipped to navigate it than if you just know a set of rules that don't even necessarily apply in that case.

Yeah, I think that we are seeing kind of like limits with approaches that are very rule based.

Or maybe my worry is like your rules can actually generalize in ways, even if they seem like good, especially if you don't give the reasons behind them.

I think they can generalize in ways that are like possibly even that like create kind of a bad character.

So suppose that you're trying to have models navigate like people who are in like difficult emotional states.

And you gave a kind of set of rules that were like, you must refer to this specific external resource.

You must take this series of steps.

And then the model encounters someone for whom those steps are simply not actually going to help them in the moment.

And so...

The ethos behind the idea that if a person is actually in need of human connection, the model should probably encourage that, that was your reasoning behind that rule.

But you didn't anticipate that for this particular person at this time and this moment, that wasn't a good thing to do.

And if the model then responds in this rule-following way,

The interesting thing is that what they're doing is, I mean, models are extremely smart.

And so they might even know this isn't what this person needs right now.

And yet I'm doing it anyway.

And I'm like the kind of person who sees another person who's like suffering or in need and knows like how to potentially help them and instead does something else.

Showing 41–60 of 338 · page 3 of 17