RSS

So8res

Karma: 19,326

Why Cor­rigi­bil­ity is Hard and Im­por­tant (i.e. “Whence the high MIRI con­fi­dence in al­ign­ment difficulty?”)

Raemon, Eliezer Yudkowsky and So8res
30 Sep 2025 0:12 UTC
78 points
50 comments17 min readLW link

The Problem

Rob Bensinger, tanagrabeast, yams, So8res, Eliezer Yudkowsky and Gretta Duleba
5 Aug 2025 21:40 UTC
313 points
218 comments26 min readLW link

A case for courage, when speak­ing of AI danger

So8res27 Jun 2025 2:15 UTC
519 points
128 comments6 min readLW link

Eliezer and I wrote a book: If Any­one Builds It, Every­one Dies

So8res14 May 2025 19:00 UTC
648 points
114 comments2 min readLW link

LessWrong: After Dark, a new side of LessWrong

So8res1 Apr 2024 22:44 UTC
36 points
6 comments1 min readLW link

Ronny and Nate dis­cuss what sorts of minds hu­man­ity is likely to find by Ma­chine Learning

So8res and Ronny Fernandez
19 Dec 2023 23:39 UTC
42 points
30 comments25 min readLW link

Quick takes on “AI is easy to con­trol”

So8res2 Dec 2023 22:31 UTC
26 points
49 comments4 min readLW link

Apoca­lypse in­surance, and the hardline liber­tar­ian take on AI risk

So8res28 Nov 2023 2:09 UTC
135 points
40 comments7 min readLW link1 review

Abil­ity to solve long-hori­zon tasks cor­re­lates with want­ing things in the be­hav­iorist sense

So8res24 Nov 2023 17:37 UTC
204 points
84 comments5 min readLW link1 review

How much to up­date on re­cent AI gov­er­nance moves?

habryka and So8res
16 Nov 2023 23:46 UTC
112 points
5 comments29 min readLW link

Thoughts on the AI Safety Sum­mit com­pany policy re­quests and responses

So8res31 Oct 2023 23:54 UTC
169 points
14 comments10 min readLW link

AI as a sci­ence, and three ob­sta­cles to al­ign­ment strategies

So8res25 Oct 2023 21:00 UTC
194 points
80 comments11 min readLW link

A mind needn’t be cu­ri­ous to reap the benefits of curiosity

So8res2 Jun 2023 18:00 UTC
78 points
14 comments1 min readLW link

Cos­mopoli­tan val­ues don’t come free

So8res31 May 2023 15:58 UTC
138 points
87 comments1 min readLW link

Sen­tience matters

So8res29 May 2023 21:25 UTC
144 points
96 comments2 min readLW link

Re­quest: stop ad­vanc­ing AI capabilities

So8res26 May 2023 17:42 UTC
154 points
24 comments1 min readLW link

Would we even want AI to solve all our prob­lems?

So8res21 Apr 2023 18:04 UTC
98 points
15 comments2 min readLW link

How could you pos­si­bly choose what an AI wants?

So8res19 Apr 2023 17:08 UTC
109 points
19 comments1 min readLW link

But why would the AI kill us?

So8res17 Apr 2023 18:42 UTC
140 points
96 comments2 min readLW link

Mis­gen­er­al­iza­tion as a misnomer

So8res6 Apr 2023 20:43 UTC
128 points
22 comments4 min readLW link