AI Robustness

Edited by markov last updated 24th Oct 2022

AI Robustness is an agents ability to maintain its goal and its capabilities when exposed to different data distributions or environments.

Posts tagged AI Robustness

133Robustness to Scale

Ω

Scott Garrabrant

8y

Ω

23

70AI Safety in a World of Vulnerable Machine Learning Systems

Ω

AdamGleave, EuanMcLean

3y

Ω

29

38Robustness to Scaling Down: More Important Than I Thought

Ω

adamShimi

3y

Ω

5

22Do the Safety Properties of Powerful AI Systems Need to be Adversarially Robust? Why?

Q

DragonGod

3y

Q

42

16Squeezing foundations research assistance out of formal logic narrow AI.

Ω

Donald Hobson

3y

Ω

1

16AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler

Ω

DanielFilan

3y

Ω

0

9Desiderata for an AI

Nathan Helm-Burger

2y

0

-11Random Observation on AI goals

[anonymous]2y

2

41What's new at FAR AI

Ω

AdamGleave, EuanMcLean

2y

Ω

0

41Beyond the Board: Exploring AI Robustness Through Go

Ω

AdamGleave

1y

Ω

2

19Why Eliminating Deception Won’t Align AI

Priyanka Bharadwaj

2mo

6

182023 Alignment Research Updates from FAR AI

Ω

AdamGleave, EuanMcLean

2y

Ω

0

14Does robustness improve with scale?

Ω

ChengCheng, niki.h, Ian McKenzie, Oskar Hollinsworth, Tom Tseng, AdamGleave

1y

Ω

0

11On Interpretability's Robustness

WCargo

2y

0

10Robustness & Evolution [MLAISU W02]

Esben Kran

3y

0

LESSWRONG
LW

LESSWRONG
LW

AI Robustness