RSS

So8res

Karma: 16,437

Truth and Ad­van­tage: Re­sponse to a draft of “AI safety seems hard to mea­sure”

So8resMar 22, 2023, 3:36 AM
98 points
10 comments5 min readLW link1 review

Deep Deceptiveness

So8resMar 21, 2023, 2:51 AM
247 points
60 comments14 min readLW link1 review

Com­ments on OpenAI’s “Plan­ning for AGI and be­yond”

So8resMar 3, 2023, 11:01 PM
148 points
2 comments14 min readLW link

Ene­mies vs Malefactors

So8resFeb 28, 2023, 11:38 PM
216 points
69 comments1 min readLW link4 reviews

AI al­ign­ment re­searchers don’t (seem to) stack

So8resFeb 21, 2023, 12:48 AM
193 points
40 comments3 min readLW link

Hash­ing out long-stand­ing dis­agree­ments seems low-value to me

So8resFeb 16, 2023, 6:20 AM
141 points
34 comments4 min readLW link

Fo­cus on the places where you feel shocked ev­ery­one’s drop­ping the ball

So8resFeb 2, 2023, 12:27 AM
454 points
63 comments4 min readLW link3 reviews

What I mean by “al­ign­ment is in large part about mak­ing cog­ni­tion aimable at all”

So8resJan 30, 2023, 3:22 PM
170 points
25 comments2 min readLW link

K-com­plex­ity is silly; use cross-en­tropy instead

So8resDec 20, 2022, 11:06 PM
147 points
54 comments14 min readLW link2 reviews

Thoughts on AGI or­ga­ni­za­tions and ca­pa­bil­ities work

Dec 7, 2022, 7:46 PM
102 points
17 comments5 min readLW link

Dist­in­guish­ing test from training

So8resNov 29, 2022, 9:41 PM
72 points
11 comments6 min readLW link

How could we know that an AGI sys­tem will have good con­se­quences?

So8resNov 7, 2022, 10:42 PM
111 points
25 comments5 min readLW link

Su­per­in­tel­li­gent AI is nec­es­sary for an amaz­ing fu­ture, but far from sufficient

So8resOct 31, 2022, 9:16 PM
132 points
48 comments34 min readLW link

So8res’s Shortform

So8resOct 27, 2022, 5:41 PM
8 points
23 comments1 min readLW link

Notes on “Can you con­trol the past”

So8resOct 20, 2022, 3:41 AM
64 points
41 comments21 min readLW link

De­ci­sion the­ory does not im­ply that we get to have nice things

So8resOct 18, 2022, 3:04 AM
171 points
73 comments26 min readLW link2 reviews

Con­tra shard the­ory, in the con­text of the di­a­mond max­i­mizer problem

So8resOct 13, 2022, 11:51 PM
105 points
19 comments2 min readLW link1 review

Nice­ness is unnatural

So8resOct 13, 2022, 1:30 AM
130 points
20 comments8 min readLW link1 review

Don’t leave your finger­prints on the future

So8resOct 8, 2022, 12:35 AM
131 points
48 comments5 min readLW link

What does it mean for an AGI to be ‘safe’?

So8resOct 7, 2022, 4:13 AM
74 points
29 comments3 min readLW link