RSS

porby

Karma: 1,870

Soft Prompts for Eval­u­a­tion: Mea­sur­ing Con­di­tional Dis­tance of Capabilities

porbyFeb 2, 2024, 5:49 AM
47 points
1 comment4 min readLW link
(1drv.ms)

FAQ: What the heck is goal ag­nos­ti­cism?

porbyOct 8, 2023, 7:11 PM
66 points
36 comments28 min readLW link

A plea for more fund­ing short­fall transparency

porbyAug 7, 2023, 9:33 PM
73 points
4 comments2 min readLW link

Us­ing pre­dic­tors in cor­rigible systems

porbyJul 19, 2023, 10:29 PM
19 points
6 comments27 min readLW link

One path to co­her­ence: con­di­tion­al­iza­tion

porbyJun 29, 2023, 1:08 AM
28 points
4 comments4 min readLW link

One im­ple­men­ta­tion of reg­u­la­tory GPU restrictions

porbyJun 4, 2023, 8:34 PM
42 points
6 comments5 min readLW link

porby’s Shortform

porbyMay 24, 2023, 9:34 PM
6 points
20 comments1 min readLW link

Im­plied “util­ities” of simu­la­tors are broad, dense, and shallow

porbyMar 1, 2023, 3:23 AM
45 points
7 comments3 min readLW link

In­stru­men­tal­ity makes agents agenty

porbyFeb 21, 2023, 4:28 AM
20 points
7 comments6 min readLW link

[Question] How would you use video gamey tech to help with AI safety?

porbyFeb 9, 2023, 12:20 AM
9 points
5 comments1 min readLW link

Against Boltz­mann mesaoptimizers

porbyJan 30, 2023, 2:55 AM
76 points
6 comments4 min readLW link

FFMI Gains: A List of Vitalities

porbyJan 12, 2023, 4:48 AM
26 points
3 comments7 min readLW link

Si­mu­la­tors, con­straints, and goal ag­nos­ti­cism: por­bynotes vol. 1

porbyNov 23, 2022, 4:22 AM
37 points
2 comments35 min readLW link

Am I se­cretly ex­cited for AI get­ting weird?

porbyOct 29, 2022, 10:16 PM
116 points
4 comments4 min readLW link

Why I think strong gen­eral AI is com­ing soon

porbySep 28, 2022, 5:40 AM
336 points
141 comments34 min readLW link1 review

Pri­vate al­ign­ment re­search shar­ing and coordination

porbySep 4, 2022, 12:01 AM
62 points
13 comments5 min readLW link