Leav­ing Orbit

Rob BensingerDec 6, 2021, 9:48 PM
50 points
17 comments1 min readLW link

Declus­ter­ing, reclus­ter­ing, and filling in thingspace

Stuart_ArmstrongDec 6, 2021, 8:53 PM
16 points
6 comments3 min readLW link

More Chris­ti­ano, Co­tra, and Yud­kowsky on AI progress

Dec 6, 2021, 8:33 PM
91 points
28 comments40 min readLW link

Are there al­ter­na­tive to solv­ing value trans­fer and ex­trap­o­la­tion?

Stuart_ArmstrongDec 6, 2021, 6:53 PM
20 points
8 comments5 min readLW link

Im­pli­ca­tions of the Grabby Aliens Model

harsimonyDec 6, 2021, 6:34 PM
2 points
3 comments2 min readLW link
(harsimony.wordpress.com)

A Pos­si­ble Re­s­olu­tion To Spu­ri­ous Counterfactuals

JoshuaOSHickmanDec 6, 2021, 6:26 PM
15 points
5 comments4 min readLW link

In­for­ma­tion bot­tle­neck for coun­ter­fac­tual corrigibility

tailcalledDec 6, 2021, 5:11 PM
8 points
1 comment7 min readLW link

Omicron Post #4

ZviDec 6, 2021, 5:00 PM
153 points
66 comments15 min readLW link
(thezvi.wordpress.com)

Life, strug­gle, and the psy­cholog­i­cal fal­lout from COVID

Alex FlintDec 6, 2021, 4:59 PM
15 points
1 comment8 min readLW link

Model­ing Failure Modes of High-Level Ma­chine Intelligence

Dec 6, 2021, 1:54 PM
54 points
1 comment12 min readLW link

A Frame­work to Ex­plain Bayesian Models

JsevillamolDec 6, 2021, 10:38 AM
27 points
1 comment8 min readLW link

Anti-cor­re­lated causation

DirectedEvolutionDec 6, 2021, 4:36 AM
18 points
2 comments3 min readLW link

ML Align­ment The­ory Pro­gram un­der Evan Hubinger

Dec 6, 2021, 12:03 AM
82 points
3 comments2 min readLW link

[Question] Are limited-hori­zon agents a good heuris­tic for the off-switch prob­lem?

Yonadav ShavitDec 5, 2021, 7:27 PM
14 points
19 comments1 min readLW link

Ex­plicit model visualizations

Dorian Stern vukoticDec 5, 2021, 6:37 PM
12 points
0 comments12 min readLW link

[Question] What would be the pros and cons of a gov­ern­ment-backed, prop­erty-based cryp­tocur­rency?

AsgårdDec 5, 2021, 5:57 PM
−3 points
6 comments2 min readLW link

In­ter­pret­ing Yud­kowsky on Deep vs Shal­low Knowledge

adamShimiDec 5, 2021, 5:32 PM
100 points
32 comments24 min readLW link

Scott Alexan­der’s “Iver­mectin: Much More Than You Wanted To Know”

RaemonDec 5, 2021, 5:43 AM
13 points
2 comments1 min readLW link2 reviews
(astralcodexten.substack.com)

[Question] What have your ro­man­tic ex­pe­riences with non-EAs/​non-Ra­tion­al­ists been like?

Randomized, ControlledDec 5, 2021, 4:41 AM
46 points
24 comments1 min readLW link

Be­hav­ior Clon­ing is Miscalibrated

leogaoDec 5, 2021, 1:36 AM
77 points
3 comments3 min readLW link

Pri­vacy and Manipulation

RaemonDec 5, 2021, 12:39 AM
80 points
41 comments8 min readLW link

Covid Christmas

jefftkDec 4, 2021, 10:00 PM
20 points
6 comments2 min readLW link
(www.jefftk.com)

A Gen­er­al­iza­tion of ROC AUC for Bi­nary Classifiers

Adam ScherlisDec 4, 2021, 9:47 PM
10 points
0 comments2 min readLW link
(adam.scherlis.com)

Agents as P₂B Chain Reactions

Daniel KokotajloDec 4, 2021, 9:35 PM
18 points
0 comments2 min readLW link

Agency: What it is and why it matters

Daniel KokotajloDec 4, 2021, 9:32 PM
25 points
2 comments2 min readLW link

Ad­vanc­ing Math­e­mat­ics By Guid­ing Hu­man In­tu­ition With AI

intersticeDec 4, 2021, 8:00 PM
5 points
0 comments1 min readLW link
(www.nature.com)

[Question] Misc. ques­tions about EfficientZero

Daniel KokotajloDec 4, 2021, 7:45 PM
51 points
17 comments1 min readLW link

Lars Doucet’s Ge­or­gism se­ries on As­tral Codex Ten

Lars DoucetDec 4, 2021, 7:43 PM
21 points
2 comments37 min readLW link1 review
(astralcodexten.substack.com)

[Question] What are the limi­ta­tions on poli­ti­cally mo­ti­vated re­lo­ca­tion?

AsgårdDec 4, 2021, 3:16 PM
9 points
2 comments1 min readLW link

[Question] Should we post­pone get­ting a booster due to Omicron, till there are Omicron-spe­cific boost­ers?

ChristianKlDec 4, 2021, 12:46 PM
33 points
18 comments1 min readLW link

Can solip­sism be dis­proven?

nx2059Dec 4, 2021, 8:24 AM
−2 points
6 comments2 min readLW link

Shul­man and Yud­kowsky on AI progress

Dec 3, 2021, 8:05 PM
90 points
16 comments20 min readLW link

[Linkpost] A Gen­eral Lan­guage As­sis­tant as a Lab­o­ra­tory for Alignment

Quintin PopeDec 3, 2021, 7:42 PM
37 points
2 comments2 min readLW link

Browser Engines

jefftkDec 3, 2021, 7:30 PM
24 points
0 comments2 min readLW link
(www.jefftk.com)

The Learn­ing System

Henrik KarlssonDec 3, 2021, 7:08 PM
18 points
12 comments10 min readLW link
(escapingflatland.substack.com)

[Question] Does the Struc­ture of an al­gorithm mat­ter for AI Risk and/​or con­scious­ness?

Logan ZoellnerDec 3, 2021, 6:31 PM
7 points
4 comments1 min readLW link

A Med­i­ta­tive Experience

Yonatan CaleDec 3, 2021, 5:58 PM
4 points
1 comment4 min readLW link

$100/​$50 re­wards for good references

Stuart_ArmstrongDec 3, 2021, 4:55 PM
20 points
5 comments1 min readLW link

[Question] Where in the world will a UBI de­velop first?

AsgårdDec 3, 2021, 3:54 PM
4 points
10 comments1 min readLW link

Rus­sian x-risks newslet­ter fall 2021

avturchinDec 3, 2021, 1:06 PM
29 points
2 comments1 min readLW link

Se­cond-or­der se­lec­tion against the immortal

MalmesburyDec 3, 2021, 5:01 AM
45 points
47 comments6 min readLW link

For­mal­iz­ing Policy-Mod­ifi­ca­tion Corrigibility

TurnTroutDec 3, 2021, 1:31 AM
25 points
6 comments6 min readLW link

Fore­cast­ing Newslet­ter: Novem­ber 2021

NunoSempereDec 2, 2021, 9:44 PM
18 points
2 comments6 min readLW link

“In­fo­haz­ard” is a pre­dom­i­nantly con­flict-the­o­retic concept

jessicataDec 2, 2021, 5:54 PM
45 points
17 comments14 min readLW link
(unstableontology.com)

Covid 12/​2: But Aside From That

ZviDec 2, 2021, 4:20 PM
36 points
11 comments9 min readLW link
(thezvi.wordpress.com)

Omicron Post #3

ZviDec 2, 2021, 3:10 PM
57 points
15 comments13 min readLW link
(thezvi.wordpress.com)

Built-in Mea­sur­ing Spoons

jefftkDec 2, 2021, 1:20 PM
10 points
0 comments1 min readLW link
(www.jefftk.com)

Covid Pre­dic­tion Mar­kets at Polymarket

ZviDec 2, 2021, 12:50 PM
39 points
10 comments7 min readLW link
(thezvi.wordpress.com)

Syd­ney AI Safety Fellowship

Chris_LeongDec 2, 2021, 7:34 AM
22 points
0 comments2 min readLW link

Mo­ral­ity is Scary

Wei DaiDec 2, 2021, 6:35 AM
219 points
116 comments4 min readLW link1 review