RSS

Wei Dai

Karma: 40,316

I think I need more practice talking with people in real time (about intellectual topics). (I’ve gotten much more used to text chat/​comments, which I like because it puts less time pressure on me to think and respond quickly, but I feel like I now incur a large cost due to excessively shying away from talking to people, hence the desire for practice.) If anyone wants to have a voice chat with me about a topic that I’m interested in (see my recent post/​comment history to get a sense), please contact me via PM.

www.weidai.com

Don’t de­pend on oth­ers to ask for explanations

Wei DaiSep 18, 2019, 7:12 PM
77 points
10 comments1 min readLW link

Coun­ter­fac­tual Or­a­cles = on­line su­per­vised learn­ing with ran­dom se­lec­tion of train­ing episodes

Wei DaiSep 10, 2019, 8:29 AM
52 points
26 comments3 min readLW link

AI Safety “Suc­cess Sto­ries”

Wei DaiSep 7, 2019, 2:54 AM
126 points
27 comments4 min readLW link1 review

Six AI Risk/​Strat­egy Ideas

Wei DaiAug 27, 2019, 12:40 AM
73 points
17 comments4 min readLW link1 review

Prob­lems in AI Align­ment that philoso­phers could po­ten­tially con­tribute to

Wei DaiAug 17, 2019, 5:38 PM
79 points
14 comments2 min readLW link

Fo­rum par­ti­ci­pa­tion as a re­search strategy

Wei DaiJul 30, 2019, 6:09 PM
153 points
45 comments3 min readLW link1 review

On the pur­poses of de­ci­sion the­ory research

Wei DaiJul 25, 2019, 7:18 AM
64 points
14 comments2 min readLW link

AGI will dras­ti­cally in­crease economies of scale

Wei DaiJun 7, 2019, 11:17 PM
65 points
26 comments1 min readLW link

How to find a lost phone with dead bat­tery, us­ing Google Lo­ca­tion His­tory Takeout

Wei DaiMay 30, 2019, 4:56 AM
53 points
5 comments1 min readLW link

[Question] Where are peo­ple think­ing and talk­ing about global co­or­di­na­tion for AI safety?

Wei DaiMay 22, 2019, 6:24 AM
112 points
22 comments1 min readLW link

“UDT2” and “against UD+ASSA”

Wei DaiMay 12, 2019, 4:18 AM
50 points
7 comments7 min readLW link

Dis­in­cen­tives for par­ti­ci­pat­ing on LW/​AF

Wei DaiMay 10, 2019, 7:46 PM
86 points
45 comments2 min readLW link

Strate­gic im­pli­ca­tions of AIs’ abil­ity to co­or­di­nate at low cost, for ex­am­ple by merging

Wei DaiApr 25, 2019, 5:08 AM
69 points
46 comments2 min readLW link1 review

Please use real names, es­pe­cially for Align­ment Fo­rum?

Wei DaiMar 29, 2019, 2:54 AM
39 points
14 comments1 min readLW link

The Main Sources of AI Risk?

Mar 21, 2019, 6:28 PM
126 points
26 comments2 min readLW link

[Question] What’s wrong with these analo­gies for un­der­stand­ing In­formed Over­sight and IDA?

Wei DaiMar 20, 2019, 9:11 AM
35 points
3 comments1 min readLW link

Three ways that “Suffi­ciently op­ti­mized agents ap­pear co­her­ent” can be false

Wei DaiMar 5, 2019, 9:52 PM
65 points
3 comments3 min readLW link

[Question] Why didn’t Agoric Com­put­ing be­come pop­u­lar?

Wei DaiFeb 16, 2019, 6:19 AM
52 points
22 comments2 min readLW link

Some dis­junc­tive rea­sons for ur­gency on AI risk

Wei DaiFeb 15, 2019, 8:43 PM
36 points
24 comments1 min readLW link

Some Thoughts on Metaphilosophy

Wei DaiFeb 10, 2019, 12:28 AM
82 points
30 comments4 min readLW link