AI ALIGNMENT FORUM
AF

Wikitags

AI Robustness

Edited by markovial 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.

Subscribe
Subscribe
Discussion0
Discussion0
Posts tagged AI Robustness
45Robustness to Scale
Scott Garrabrant
7y
7
35AI Safety in a World of Vulnerable Machine Learning Systems
AdamGleave, EuanMcLean
2y
27
18Robustness to Scaling Down: More Important Than I Thought
Adam Shimi
3y
5
7Squeezing foundations research assistance out of formal logic narrow AI.
Donald Hobson
2y
0
10AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler
DanielFilan
3y
0
19What's new at FAR AI
AdamGleave, EuanMcLean
2y
0
23Beyond the Board: Exploring AI Robustness Through Go
AdamGleave
1y
1
102023 Alignment Research Updates from FAR AI
AdamGleave, EuanMcLean
2y
0
8Does robustness improve with scale?
ChengCheng, niki.h, Ian McKenzie, Oskar Hollinsworth, Tom Tseng, AdamGleave
1y
0
Add Posts