korrents

← People and their mental models

Amanda Askell's mental models

5 claims Amanda Askell made fit 2 mental models. Most often: Margin of safety, Probabilistic thinking. Everything they said here.

Models we see in what they say

Our reading: their claim applies the idea without naming it. The claim is theirs; filing it here is ours.

Margin of safety

Leave room for being wrong, because sometimes you will be.

Used by 27 others

Being robustly tolerable matters most when the expected costs of failure are high.

  1. Amanda Askell Philosopher at Anthropic working on finetuning and AI alignment Being robustly tolerable is not a particularly valuable trait when the expected costs of failure are low, but it's an extremely valuable trait when the expected costs of failure are high. When robustly tolerable beats precariously optimal (Amanda Askell's Blog)askell.blog · 1 Jul 2020All korrents from this piece
    Being robustly tolerable is not a particularly valuable trait when the expected costs of failure are low, but it's an extremely valuable trait when the expected costs of failure are high.

The property of being robustly tolerable can be undervalued.

  1. Amanda Askell Philosopher at Anthropic working on finetuning and AI alignment I think we can undervalue the property of being robustly tolerable. When robustly tolerable beats precariously optimal (Amanda Askell's Blog)askell.blog · 1 Jul 2020All korrents from this piece
    I think we can undervalue the property of being robustly tolerable.

A political system that allows a benevolent dictatorship also puts you at much greater risk of a malevolent one.

  1. Amanda Askell Philosopher at Anthropic working on finetuning and AI alignment A benevolent dictatorship may seem surprisingly alluring in bad times, but any political system that enables a benevolent dictatorship also puts you at much greater risk of a malevolent one. When robustly tolerable beats precariously optimal (Amanda Askell's Blog)askell.blog · 1 Jul 2020All korrents from this piece
    A benevolent dictatorship may seem surprisingly alluring in bad times, but any political system that enables a benevolent dictatorship also puts you at much greater risk of a malevolent one.

Probabilistic thinking

Think in odds, not certainties, and bet heavily only when the odds are clearly yours.

Used by 26 others

For anything we try, the optimal rate of failure often is not zero.

  1. Amanda Askell Philosopher at Anthropic working on finetuning and AI alignment For anything we try to do, the optimal rate of failure often isn’t zero: in fact, sometimes it’s very, very far from zero. The optimal rate of failure (Amanda Askell's Blog)askell.blog · 15 Jun 2020All korrents from this piece
    For anything we try to do, the optimal rate of failure often isn’t zero: in fact, sometimes it’s very, very far from zero.

Never failing is a sign of being too risk averse, which is costly.

  1. Amanda Askell Philosopher at Anthropic working on finetuning and AI alignment if you find you’re never failing, there’s a good chance you’re being too risk averse, and being too risk averse is costly. The optimal rate of failure (Amanda Askell's Blog)askell.blog · 15 Jun 2020All korrents from this piece
    if you find you’re never failing, there’s a good chance you’re being too risk averse, and being too risk averse is costly.