RSS

So8res(Nate Soares)

Karma: 15,569

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

So8res2 Feb 2023 0:27 UTC
413 points
61 comments4 min readLW link

On how var­i­ous plans miss the hard bits of the al­ign­ment challenge

So8res12 Jul 2022 2:49 UTC
302 points
88 comments29 min readLW link3 reviews

Hooray for step­ping out of the limelight

So8res1 Apr 2023 2:45 UTC
281 points
24 comments1 min readLW link

A cen­tral AI al­ign­ment prob­lem: ca­pa­bil­ities gen­er­al­iza­tion, and the sharp left turn

So8res15 Jun 2022 13:10 UTC
279 points
53 comments10 min readLW link1 review

Dark Arts of Rationality

So8res19 Jan 2014 2:47 UTC
254 points
193 comments18 min readLW link

Visi­ble Thoughts Pro­ject and Bounty Announcement

So8res30 Nov 2021 0:19 UTC
249 points
103 comments13 min readLW link1 review

Deep Deceptiveness

So8res21 Mar 2023 2:51 UTC
231 points
58 comments14 min readLW link

On sav­ing the world

So8res30 Jan 2014 20:00 UTC
227 points
171 comments16 min readLW link

On Caring

So8res15 Oct 2014 1:59 UTC
225 points
276 comments10 min readLW link

Ene­mies vs Malefactors

So8res28 Feb 2023 23:38 UTC
203 points
60 comments1 min readLW link

On learn­ing difficult things

So8res11 Nov 2013 23:35 UTC
202 points
47 comments6 min readLW link

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

So8res24 Nov 2023 17:37 UTC
202 points
82 comments5 min readLW link

The me­chan­ics of my re­cent productivity

So8res9 Jan 2014 2:30 UTC
199 points
47 comments9 min readLW link

If in­ter­pretabil­ity re­search goes well, it may get dangerous

So8res3 Apr 2023 21:48 UTC
197 points
10 comments2 min readLW link

A note about differ­en­tial tech­nolog­i­cal development

So8res15 Jul 2022 4:46 UTC
192 points
32 comments6 min readLW link

AI al­ign­ment re­searchers don’t (seem to) stack

So8res21 Feb 2023 0:48 UTC
189 points
40 comments3 min readLW link

A rough and in­com­plete re­view of some of John Went­worth’s research

So8res28 Mar 2023 18:52 UTC
175 points
17 comments18 min readLW link

AI as a sci­ence, and three ob­sta­cles to al­ign­ment strategies

So8res25 Oct 2023 21:00 UTC
175 points
79 comments11 min readLW link

AGI ruin sce­nar­ios are likely (and dis­junc­tive)

So8res27 Jul 2022 3:21 UTC
170 points
38 comments6 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