RSS

capybaralet(David Krueger)

Karma: 879

[Question] Is there a name for the the­ory that “There will be fast take­off in real-world ca­pa­bil­ities be­cause al­most ev­ery­thing is AGI-com­plete”?

capybaralet2 Sep 2021 23:00 UTC
31 points
7 comments1 min readLW link

[Question] What do we know about how much pro­tec­tion COVID vac­cines provide against trans­mit­ting the virus to oth­ers?

capybaralet6 May 2021 7:39 UTC
9 points
0 comments1 min readLW link

[Question] What do we know about how much pro­tec­tion COVID vac­cines provide against long COVID?

capybaralet6 May 2021 7:39 UTC
8 points
0 comments1 min readLW link

[Question] What do the re­ported lev­els of pro­tec­tion offered by var­i­ous vac­cines mean?

capybaralet4 May 2021 22:06 UTC
10 points
4 comments1 min readLW link

[Question] Did they use serolog­i­cal test­ing for COVID vac­cine tri­als?

capybaralet4 May 2021 21:48 UTC
4 points
0 comments1 min readLW link

[Question] When’s the best time to get the 2nd dose of Pfizer Vac­cine?

capybaralet30 Apr 2021 5:11 UTC
5 points
3 comments1 min readLW link

[Question] Are there any good ways to place a bet on Rad­i­calXChange and/​or re­lated ideas/​mechanisms tak­ing off in a big way? e.g. is there some­thing to in­vest $$$ in?

capybaralet17 Apr 2021 6:58 UTC
2 points
0 comments1 min readLW link

[Question] What does vac­cine effec­tive­ness as a func­tion of time look like?

capybaralet17 Apr 2021 0:36 UTC
18 points
8 comments1 min readLW link

[Question] How many micro­morts do you get per UV-in­dex-hour?

capybaralet30 Mar 2021 17:23 UTC
20 points
9 comments1 min readLW link

AI x-risk re­duc­tion: why I chose academia over industry

capybaralet14 Mar 2021 17:25 UTC
52 points
13 comments3 min readLW link

“Beliefs” vs. “No­tions”

capybaralet12 Mar 2021 16:04 UTC
12 points
7 comments1 min readLW link

[Question] Any work on hon­ey­pots (to de­tect treach­er­ous turn at­tempts)?

capybaralet12 Nov 2020 5:41 UTC
17 points
4 comments1 min readLW link

[Question] When was the term “AI al­ign­ment” coined?

capybaralet21 Oct 2020 18:27 UTC
11 points
8 comments1 min readLW link

[Question] Has any­one re­searched speci­fi­ca­tion gam­ing with biolog­i­cal an­i­mals?

capybaralet21 Oct 2020 0:20 UTC
9 points
3 comments1 min readLW link

[Question] Is there any work on in­cor­po­rat­ing aleatoric un­cer­tainty and/​or in­her­ent ran­dom­ness into AIXI?

capybaralet4 Oct 2020 8:10 UTC
7 points
7 comments1 min readLW link

capy­bar­alet’s Shortform

capybaralet27 Aug 2020 21:38 UTC
5 points
41 comments1 min readLW link

A re­duc­tio ad ab­sur­dum for naive Func­tional/​Com­pu­ta­tional The­ory-of-Mind (FCToM).

capybaralet2 Jan 2020 17:16 UTC
3 points
2 comments1 min readLW link

A list of good heuris­tics that the case for AI x-risk fails

capybaralet2 Dec 2019 19:26 UTC
23 points
14 comments2 min readLW link

What I talk about when I talk about AI x-risk: 3 core claims I want ma­chine learn­ing re­searchers to ad­dress.

capybaralet2 Dec 2019 18:20 UTC
28 points
13 comments3 min readLW link

A fun cal­ibra­tion game: “0-hit Google phrases”

capybaralet21 Nov 2019 1:13 UTC
6 points
1 comment1 min readLW link