paulfchristiano

Karma: 28,843

Announcing the ARC White-Box Estimation Challenge

Jacob_Hilton, paulfchristiano and Wilson Wu

2 Jun 2026 16:20 UTC

165 points

19 comments3 min readLW link

(www.alignment.org)

Mechanistic estimation for expectations of random products

Jacob_Hilton, George Robinson, Eric Neyman, paulfchristiano, Mikewins, Victor Lecomte, Wilson Wu and Gabriel Wu

15 May 2026 16:50 UTC

50 points

0 comments5 min readLW link

(www.alignment.org)

Matrix completion prize results

paulfchristiano20 Dec 2023 15:40 UTC

45 points

0 comments2 min readLW link

(www.alignment.org)

Thoughts on responsible scaling policies and regulation

paulfchristiano24 Oct 2023 22:21 UTC

220 points

34 comments6 min readLW link

Thoughts on sharing information about language model capabilities

paulfchristiano31 Jul 2023 16:04 UTC

211 points

44 comments11 min readLW link 1 review

Self-driving car bets

paulfchristiano29 Jul 2023 18:10 UTC

237 points

46 comments5 min readLW link

(sideways-view.com)

ARC is hiring theoretical researchers

paulfchristiano, Jacob_Hilton and Mark Xu

12 Jun 2023 18:50 UTC

126 points

12 comments4 min readLW link

(www.alignment.org)

Prizes for matrix completion problems

paulfchristiano3 May 2023 23:30 UTC

164 points

52 comments1 min readLW link

(www.alignment.org)

My views on “doom”

paulfchristiano27 Apr 2023 17:50 UTC

253 points

38 comments2 min readLW link 1 review

(ai-alignment.com)

Christiano (ARC) and GA (Conjecture) Discuss Alignment Cruxes

Andrea_Miotti, paulfchristiano, Gabriel Alfour and Olive Branch

24 Feb 2023 23:03 UTC

61 points

7 comments47 min readLW link

Thoughts on the impact of RLHF research

paulfchristiano25 Jan 2023 17:23 UTC

255 points

102 comments9 min readLW link

Can we efficiently distinguish different mechanisms?

paulfchristiano27 Dec 2022 0:20 UTC

91 points

30 comments16 min readLW link

(ai-alignment.com)

Three reasons to cooperate

paulfchristiano24 Dec 2022 17:40 UTC

86 points

14 comments10 min readLW link

(sideways-view.com)

Can we efficiently explain model behaviors?

paulfchristiano16 Dec 2022 19:40 UTC

64 points

3 comments9 min readLW link

(ai-alignment.com)

AI alignment is distinct from its near-term applications

paulfchristiano13 Dec 2022 7:10 UTC

255 points

21 comments2 min readLW link

(ai-alignment.com)

Finding gliders in the game of life

paulfchristiano1 Dec 2022 20:40 UTC

104 points

8 comments16 min readLW link

(ai-alignment.com)

Mechanistic anomaly detection and ELK

paulfchristiano25 Nov 2022 18:50 UTC

138 points

22 comments21 min readLW link

(ai-alignment.com)

Decision theory and dynamic inconsistency

paulfchristiano3 Jul 2022 22:20 UTC

85 points

35 comments10 min readLW link

(sideways-view.com)

AI-Written Critiques Help Humans Notice Flaws

paulfchristiano25 Jun 2022 17:22 UTC

137 points

5 comments3 min readLW link

(openai.com)

Where I agree and disagree with Eliezer

paulfchristiano19 Jun 2022 19:15 UTC

933 points

224 comments18 min readLW link 2 reviews