AI safety @ Harvard  / ex-finance  / interpretability research  / painting

Anastasia
Ahani

I'm interested in interpretability

What I do

01 / 04
01Look inside

Interpret­ability
02Look out

AI Safety
03Look slowly

Painting

Who I am

02 / 04
Portrait of Anastasia

Talks & slides

03 / 04

AI Safety: No Longer a Theoretical Problem

Goldman Sachs Investment Strategy Group, New York
Slides ↗ Video ▶

Lately writing

04 / 04

The Value of Inconveniencing Yourself

The world doesn't need more people who are optimized. It needs more people who are willing to be interrupted.

 All posts →