RSS

Yitz

Karma: 1,449

I’m an artist, writer, and human being.

To be a little more precise: I make video games, edit Wikipedia, and write here on LessWrong!

[Linkpost] Solv­ing Quan­ti­ta­tive Rea­son­ing Prob­lems with Lan­guage Models

Yitz30 Jun 2022 18:58 UTC
67 points
12 comments2 min readLW link
(storage.googleapis.com)

Depen­den­cies for AGI pessimism

Yitz24 Jun 2022 22:25 UTC
6 points
4 comments1 min readLW link

[Question] What’s the con­tin­gency plan if we get AGI to­mor­row?

Yitz23 Jun 2022 3:10 UTC
61 points
24 comments1 min readLW link

Loose thoughts on AGI risk

Yitz23 Jun 2022 1:02 UTC
7 points
3 comments1 min readLW link

[Linkpost & Dis­cus­sion] AI Trained on 4Chan Be­comes ‘Hate Speech Ma­chine’ [and out­performs GPT-3 on Truth­fulQA Bench­mark?!]

Yitz9 Jun 2022 10:59 UTC
16 points
5 comments2 min readLW link
(www.vice.com)

The Prob­lem With The Cur­rent State of AGI Definitions

Yitz29 May 2022 13:58 UTC
40 points
21 comments8 min readLW link

Pos­i­tive out­comes un­der an un­al­igned AGI takeover

Yitz12 May 2022 7:45 UTC
19 points
12 comments3 min readLW link

[Question] Con­vince me that hu­man­ity *isn’t* doomed by AGI

Yitz15 Apr 2022 17:26 UTC
60 points
53 comments1 min readLW link

[Question] Con­vince me that hu­man­ity is as doomed by AGI as Yud­kowsky et al., seems to believe

Yitz10 Apr 2022 21:02 UTC
91 points
142 comments2 min readLW link

[Question] List of con­crete hy­po­thet­i­cals for AI takeover?

Yitz7 Apr 2022 16:54 UTC
7 points
5 comments1 min readLW link

Test­ing PaLM prompts on GPT3

Yitz6 Apr 2022 5:21 UTC
101 points
15 comments8 min readLW link

[Question] If you lose enough Good Heart To­kens, will you lose real-world money?

Yitz1 Apr 2022 21:11 UTC
9 points
0 comments1 min readLW link

Meta wants to use AI to write Wikipe­dia ar­ti­cles; I am Ner­vous™

Yitz30 Mar 2022 19:05 UTC
14 points
12 comments1 min readLW link

[Question] What would make you con­fi­dent that AGI has been achieved?

Yitz29 Mar 2022 23:02 UTC
17 points
6 comments1 min readLW link

[Question] How many gen­er­als does Rus­sia have left?

Yitz27 Mar 2022 23:11 UTC
14 points
17 comments1 min readLW link

An out­line of an ironic LessWrong post

Yitz25 Mar 2022 22:51 UTC
−8 points
4 comments1 min readLW link

Why Mir­a­cles Should Not Be Used as a Rea­son to Believe in a Religion

Yitz23 Mar 2022 20:53 UTC
−2 points
6 comments2 min readLW link

[Question] Danger(s) of the­o­rem-prov­ing AI?

Yitz16 Mar 2022 2:47 UTC
7 points
9 comments1 min readLW link

[Question] In­fo­haz­ards, hack­ing, and Brick­ing—how to for­mal­ize these con­cepts?

Yitz10 Mar 2022 16:42 UTC
4 points
11 comments4 min readLW link

[Question] What are some low-cog­ni­tive -work­load tasks that can help im­prove the world?

Yitz1 Mar 2022 17:47 UTC
29 points
12 comments1 min readLW link