RSS

In­fra-Bayesian phys­i­cal­ism: proofs part II

Vanessa Kosoy30 Nov 2021 22:27 UTC
7 points
0 comments23 min readLW link

In­fra-Bayesian phys­i­cal­ism: proofs part I

Vanessa Kosoy30 Nov 2021 22:26 UTC
7 points
0 comments22 min readLW link

In­fra-Bayesian phys­i­cal­ism: a for­mal the­ory of nat­u­ral­ized induction

Vanessa Kosoy30 Nov 2021 22:25 UTC
37 points
0 comments39 min readLW link

My take on higher-or­der game theory

Nisan30 Nov 2021 5:56 UTC
24 points
2 comments5 min readLW link

Visi­ble Thoughts Pro­ject and Bounty Announcement

So8res30 Nov 2021 0:19 UTC
199 points
61 comments12 min readLW link

Soares, Tal­linn, and Yud­kowsky dis­cuss AGI cognition

29 Nov 2021 19:26 UTC
99 points
22 comments40 min readLW link

Com­ments on Allan Dafoe on AI Governance

alexflint29 Nov 2021 16:16 UTC
16 points
0 comments7 min readLW link

Solve Cor­rigi­bil­ity Week

elriggs28 Nov 2021 17:00 UTC
39 points
15 comments1 min readLW link

Chris­ti­ano, Co­tra, and Yud­kowsky on AI progress

25 Nov 2021 16:45 UTC
103 points
82 comments68 min readLW link

[AN #169]: Col­lab­o­rat­ing with hu­mans with­out hu­man data

rohinmshah24 Nov 2021 18:30 UTC
33 points
0 comments8 min readLW link
(mailchi.mp)

AI Tracker: mon­i­tor­ing cur­rent and near-fu­ture risks from su­per­scale models

23 Nov 2021 19:16 UTC
59 points
7 comments3 min readLW link
(aitracker.org)

AI Safety Needs Great Engineers

Andy Jones23 Nov 2021 15:40 UTC
75 points
33 comments4 min readLW link

In­te­grat­ing Three Models of (Hu­man) Cognition

jbkjr23 Nov 2021 1:06 UTC
26 points
1 comment32 min readLW link

Po­ten­tial Align­ment men­tal tool: Keep­ing track of the types

Donald Hobson22 Nov 2021 20:05 UTC
28 points
1 comment2 min readLW link

Yud­kowsky and Chris­ti­ano dis­cuss “Take­off Speeds”

Eliezer Yudkowsky22 Nov 2021 19:35 UTC
171 points
157 comments60 min readLW link

Mo­rally un­der­defined situ­a­tions can be deadly

Stuart_Armstrong22 Nov 2021 14:48 UTC
17 points
8 comments2 min readLW link

From lan­guage to ethics by au­to­mated reasoning

Michele Campolo21 Nov 2021 15:16 UTC
4 points
5 comments6 min readLW link

Cor­rigi­bil­ity Can Be VNM-Incoherent

TurnTrout20 Nov 2021 0:30 UTC
61 points
23 comments7 min readLW link

More de­tailed pro­posal for mea­sur­ing al­ign­ment of cur­rent models

Beth Barnes20 Nov 2021 0:03 UTC
27 points
0 comments8 min readLW link

Good­hart: Endgame

Charlie Steiner19 Nov 2021 1:26 UTC
22 points
3 comments7 min readLW link