5 Feb 2023 22:02 UTC

663 points

204 comments12 min readLW link

Are short timelines actually bad?

joshc5 Feb 2023 21:21 UTC

56 points

7 comments3 min readLW link

Stanzas On Power Calculation

DirectedEvolution5 Feb 2023 19:15 UTC

9 points

0 comments1 min readLW link

A List of things I might do with a Proof Oracle

Logan Zoellner5 Feb 2023 18:14 UTC

−14 points

13 comments3 min readLW link

Teaching Simple Boundaries

jefftk5 Feb 2023 17:30 UTC

23 points

0 comments2 min readLW link

(www.jefftk.com)

Control

TsviBT5 Feb 2023 16:16 UTC

19 points

14 comments9 min readLW link

Have an idea? Come to Oxford to discuss and write (20 – 24 March)

RP, Flourish Journal and Jemima

5 Feb 2023 15:05 UTC

20 points

0 comments1 min readLW link

H5N1 - thread for information sharing, planning, and action

MathiasKB5 Feb 2023 12:44 UTC

31 points

8 comments1 min readLW link

Second call: CFP for Rebellion and Disobedience in AI workshop

Ram Rachum5 Feb 2023 12:18 UTC

2 points

0 comments2 min readLW link

Research Direction: Be the AGI you want to see in the world

scottviteri, sudo and Lauro Langosco

5 Feb 2023 7:15 UTC

43 points

0 comments7 min readLW link

Sex is Good, Actually

Gordon Seidoh Worley5 Feb 2023 6:33 UTC

40 points

8 comments4 min readLW link

Questions about AI that bother me

Eleni Angelou5 Feb 2023 5:04 UTC

13 points

6 comments2 min readLW link

Evaluations (of new AI Safety researchers) can be noisy

LawrenceC5 Feb 2023 4:15 UTC

130 points

10 comments16 min readLW link

Pandemic Prediction Checklist: H5N1

DirectedEvolution5 Feb 2023 3:26 UTC

42 points

9 comments7 min readLW link

Podcast with Oli Habryka on LessWrong / Lightcone Infrastructure

DanielFilan5 Feb 2023 2:52 UTC

88 points

20 comments1 min readLW link

(thefilancabinet.com)

Misleading Fast Charging Specs

jefftk5 Feb 2023 2:50 UTC

9 points

3 comments1 min readLW link

(www.jefftk.com)

I hired 5 people to sit behind me and make me productive for a month

Simon Berens5 Feb 2023 1:19 UTC

243 points

81 comments10 min readLW link

(www.simonberens.com)

Modal Fixpoint Cooperation without Löb’s Theorem

Andrew_Critch5 Feb 2023 0:58 UTC

133 points

32 comments3 min readLW link

 Who invented knitting? The plot thickens

eukaryote5 Feb 2023 0:24 UTC

60 points

9 comments19 min readLW link

(eukaryotewritesblog.com)

Some miscellaneous thoughts on ChatGPT, stories, and mechanical interpretability

Bill Benzon4 Feb 2023 19:35 UTC

2 points

0 comments3 min readLW link

O(“AGI Safety”)>O(“Stop Tyrants”)

AnthonyRepetto4 Feb 2023 18:38 UTC

−4 points

11 comments1 min readLW link

Monthly Doom Argument Threads? Doom Argument Wiki?

LVSN4 Feb 2023 16:59 UTC

3 points

0 comments1 min readLW link

The Future of Structured Self Improvement

Evenflair4 Feb 2023 16:02 UTC

27 points

4 comments1 min readLW link

(guildoftherose.org)

Empathy as a natural consequence of learnt reward models

beren4 Feb 2023 15:35 UTC

46 points

27 comments13 min readLW link

Mech Interp Project Advising Call: Memorisation in GPT-2 Small

Neel Nanda4 Feb 2023 14:17 UTC

7 points

0 comments1 min readLW link

Do IQ tests measure intelligence? - A prediction market on my future beliefs about the topic

tailcalled4 Feb 2023 11:19 UTC

1 point

10 comments1 min readLW link

(manifold.markets)

AXRP Episode 19 - Mechanistic Interpretability with Neel Nanda

DanielFilan4 Feb 2023 3:00 UTC

44 points

0 comments117 min readLW link

The 2/3 rule for multi-factor authentication

RomanHauksson4 Feb 2023 2:57 UTC

4 points

0 comments1 min readLW link

(roman.computer)

Path-Dependence in ChatGPT’s Political Outputs

lsusr4 Feb 2023 2:02 UTC

28 points

4 comments4 min readLW link

Fucking Goddamn Basics of Rationalist Discourse

LoganStrohl4 Feb 2023 1:47 UTC

301 points

97 comments1 min readLW link

Small Talk is Good, Actually

Gordon Seidoh Worley4 Feb 2023 0:38 UTC

50 points

9 comments3 min readLW link

Update on Book Review Dominant Assurance Contract

Arjun Panickssery3 Feb 2023 23:16 UTC

9 points

0 comments1 min readLW link

[Question] 2+2=π√2+n

Logan Zoellner3 Feb 2023 22:27 UTC

16 points

15 comments1 min readLW link

[Question] If I encounter a capabilities paper that kinda spooks me, what should I do with it?

the gears to ascension3 Feb 2023 21:37 UTC

28 points

8 comments1 min readLW link

[Question] What Are The Preconditions/Prerequisites for Asymptotic Analysis?

DragonGod3 Feb 2023 21:26 UTC

8 points

2 comments1 min readLW link

[Linkpost] Google invested $300M in Anthropic in late 2022

Akash3 Feb 2023 19:13 UTC

73 points

14 comments1 min readLW link

(www.ft.com)

Many AI governance proposals have a tradeoff between usefulness and feasibility

Akash and Carson Ezell

3 Feb 2023 18:49 UTC

22 points

2 comments2 min readLW link

Reply to Duncan Sabien on Strawmanning

Zack_M_Davis3 Feb 2023 17:57 UTC

41 points

11 comments4 min readLW link

Semi-rare plain language words that are great to remember

LVSN3 Feb 2023 16:33 UTC

4 points

7 comments1 min readLW link

[Question] What qualities does an AGI need to have to realize the risk of false vacuum, without hardcoding physics theories into it?

RationalSieve3 Feb 2023 16:00 UTC

1 point

4 comments1 min readLW link

Housing and Transit Roundup #3

Zvi3 Feb 2023 15:10 UTC

21 points

6 comments16 min readLW link

(thezvi.wordpress.com)

Taboo P(doom)

NathanBarnard3 Feb 2023 10:37 UTC

13 points

10 comments1 min readLW link

ChatGPT: Tantalizing afterthoughts in search of story trajectories [induction heads]

Bill Benzon3 Feb 2023 10:35 UTC

4 points

0 comments20 min readLW link

Jordan Peterson: Guru/Villain

Bryan Frances3 Feb 2023 9:02 UTC

−14 points

6 comments9 min readLW link

[Question] What is the risk of asking a counterfactual oracle a question that already had its answer erased?

Chris_Leong3 Feb 2023 3:13 UTC

7 points

0 comments1 min readLW link

I don’t think MIRI “gave up”

Raemon3 Feb 2023 0:26 UTC

105 points

64 comments4 min readLW link

What fact that you know is true but most people aren’t ready to accept it?

lorepieri3 Feb 2023 0:06 UTC

47 points

209 comments1 min readLW link

[Question] Monotonous Work

Gideon Bauer2 Feb 2023 21:35 UTC

1 point

0 comments1 min readLW link

Is AI risk assessment too anthropocentric?

Craig Mattson2 Feb 2023 21:34 UTC

3 points

6 comments1 min readLW link

Halifax Monthly Meetup: Introduction to Effective Altruism

Ideopunk2 Feb 2023 21:10 UTC

10 points

0 comments1 min readLW link