Owain_Evans

Karma: 3,336

https://owainevans.github.io/

Truthful AI: Developing and governing AI that does not lie

Owain_Evans, owencb and Lukas Finnveden

Oct 18, 2021, 6:37 PM

82 points

9 comments10 min readLW link

How truthful is GPT-3? A benchmark for language models

Owain_EvansSep 16, 2021, 10:09 AM

58 points

24 comments6 min readLW link

Owain_Evans’s Shortform

Owain_EvansJun 19, 2021, 1:17 PM

5 points

11 comments LW link

AI Safety Research Project Ideas

Owain_EvansMay 21, 2021, 1:39 PM

58 points

2 comments3 min readLW link

Solving Math Problems by Relay

Ben Goldhaber and Owain_Evans

Jul 17, 2020, 3:32 PM

103 points

26 comments7 min readLW link

Quantifying Household Transmission of COVID-19

Owain_EvansJul 6, 2020, 11:19 AM

35 points

4 comments4 min readLW link

Update on Ought’s experiments on factored evaluation of arguments

Owain_EvansJan 12, 2020, 9:20 PM

29 points

1 comment1 min readLW link

(ought.org)

Neural nets as a model for how humans make and understand visual art

Owain_EvansNov 9, 2019, 4:53 PM

28 points

7 comments2 min readLW link

(owainevans.github.io)

Machine Learning Projects on IDA

Owain_Evans, William_S and stuhlmueller

Jun 24, 2019, 6:38 PM

49 points

3 comments2 min readLW link

Model Mis-specification and Inverse Reinforcement Learning

Owain_Evans and jsteinhardt

Nov 9, 2018, 3:33 PM

34 points

3 comments16 min readLW link