2 Jan 2023 23:48 UTC

50 points

4 comments3 min readLW link

Linear Algebra Done Right, Axler

David Udell2 Jan 2023 22:54 UTC

56 points

6 comments9 min readLW link

MacArthur BART (Filk)

Gordon Seidoh Worley2 Jan 2023 22:50 UTC

10 points

1 comment1 min readLW link

Knottiness

abramdemski2 Jan 2023 22:13 UTC

43 points

4 comments2 min readLW link

[Question] Default Sort for Shortforms is Very Bad; How Do I Change It?

DragonGod2 Jan 2023 21:50 UTC

15 points

0 comments1 min readLW link

MAKE IT BETTER (a poetic demonstration of the banality of GPT-3)

rogersbacon2 Jan 2023 20:47 UTC

7 points

2 comments5 min readLW link

Review of “Make People Better”

Metacelsus2 Jan 2023 20:30 UTC

10 points

0 comments3 min readLW link

(denovo.substack.com)

Preparing for Less Privacy

jefftk2 Jan 2023 20:30 UTC

23 points

1 comment2 min readLW link

(www.jefftk.com)

Large language models can provide “normative assumptions” for learning human preferences

Stuart_Armstrong2 Jan 2023 19:39 UTC

29 points

12 comments3 min readLW link

On the Importance of Open Sourcing Reward Models

elandgre2 Jan 2023 19:01 UTC

18 points

5 comments6 min readLW link

Prediction Markets for Science

Vaniver2 Jan 2023 17:55 UTC

27 points

7 comments5 min readLW link

Why don’t Rationalists use bidets?

Lakin2 Jan 2023 17:42 UTC

31 points

33 comments2 min readLW link

Soft optimization makes the value target bigger

Jeremy Gillen2 Jan 2023 16:06 UTC

117 points

20 comments12 min readLW link

Results from the AI testing hackathon

Esben Kran2 Jan 2023 15:46 UTC

13 points

0 comments1 min readLW link

Induction heads—illustrated

CallumMcDougall2 Jan 2023 15:35 UTC

114 points

9 comments3 min readLW link

Opportunity Cost Blackmail

adamShimi2 Jan 2023 13:48 UTC

70 points

11 comments2 min readLW link

(epistemologicalvigilance.substack.com)

The ultimate limits of alignment will determine the shape of the long term future

beren2 Jan 2023 12:47 UTC

34 points

2 comments6 min readLW link

A kernel of Lie theory

Alok Singh2 Jan 2023 9:20 UTC

−1 points

8 comments1 min readLW link

(alok.github.io)

Belief Bias: Bias in Evaluating AGI X-Risks

Remmelt and flandry19

2 Jan 2023 8:59 UTC

−10 points

1 comment1 min readLW link

Pacing: inexplicably good

KatjaGrace2 Jan 2023 8:30 UTC

39 points

7 comments1 min readLW link

(worldspiritsockpuppet.com)

Alignment, Anger, and Love: Preparing for the Emergence of Superintelligent AI

tavurth2 Jan 2023 6:16 UTC

2 points

3 comments1 min readLW link

[Question] How can total world index fund growth outpace money supply growth over the long term?

pando2 Jan 2023 5:33 UTC

4 points

7 comments1 min readLW link

My first year in AI alignment

Alex_Altair2 Jan 2023 1:28 UTC

61 points

10 comments7 min readLW link

Sail Over Mountains of ICE...

AnthonyRepetto2 Jan 2023 0:27 UTC

26 points

51 comments7 min readLW link

Fun math facts about 2023

Adam Scherlis1 Jan 2023 23:38 UTC

9 points

6 comments1 min readLW link

The Thingness of Things

TsviBT1 Jan 2023 22:19 UTC

48 points

35 comments10 min readLW link

Thoughts On Expanding the AI Safety Community: Benefits and Challenges of Outreach to Non-Technical Professionals

Yashvardhan Sharma1 Jan 2023 19:21 UTC

4 points

4 comments7 min readLW link

[Question] Would it be good or bad for the US military to get involved in AI risk?

Grant Demaree1 Jan 2023 19:02 UTC

50 points

12 comments1 min readLW link

Better New Year’s Goals through Aligning the Elephant and the Rider

moridinamael1 Jan 2023 17:54 UTC

20 points

0 comments2 min readLW link

(guildoftherose.org)

A Löbian argument pattern for implicit reasoning in natural language: Löbian party invitations

Andrew_Critch1 Jan 2023 17:39 UTC

23 points

8 comments7 min readLW link

woke offline, anti-woke online

Yair Halberstadt1 Jan 2023 8:24 UTC

13 points

12 comments1 min readLW link

Summary of 80k’s AI problem profile

JakubK1 Jan 2023 7:30 UTC

7 points

0 comments5 min readLW link

(forum.effectivealtruism.org)

What percent of people work in moral mazes?

Raemon1 Jan 2023 4:33 UTC

21 points

9 comments4 min readLW link

Recursive Middle Manager Hell

Raemon1 Jan 2023 4:33 UTC

221 points

46 comments11 min readLW link 1 review

Challenge to the notion that anything is (maybe) possible with AGI

Remmelt and flandry19

1 Jan 2023 3:57 UTC

−27 points

4 comments1 min readLW link

(mflb.com)

The Roots of Progress’s 2022 in review

jasoncrawford1 Jan 2023 2:54 UTC

14 points

2 comments15 min readLW link

(rootsofprogress.org)

Investing for a World Transformed by AI

PeterMcCluskey1 Jan 2023 2:47 UTC

67 points

24 comments6 min readLW link 1 review

(bayesianinvestor.com)

Why Free Will is NOT an illusion

Akira Pyinya1 Jan 2023 2:29 UTC

0 points

16 comments1 min readLW link

Localhost Security Messaging

jefftk1 Jan 2023 2:20 UTC

7 points

3 comments1 min readLW link

(www.jefftk.com)

0 and 1 aren’t probabilities

Alok Singh1 Jan 2023 0:09 UTC

2 points

4 comments2 min readLW link

(en.wikipedia.org)

‘simulator’ framing and confusions about LLMs

Beth Barnes31 Dec 2022 23:38 UTC

104 points

11 comments4 min readLW link

Monitoring devices I have loved

Elizabeth31 Dec 2022 22:51 UTC

62 points

13 comments3 min readLW link 1 review

Slack matters more than any outcome

Valentine31 Dec 2022 20:11 UTC

156 points

56 comments19 min readLW link 1 review

To Be Particular About Morality

AGO31 Dec 2022 19:58 UTC

6 points

2 comments7 min readLW link

200 COP in MI: Interpreting Algorithmic Problems

Neel Nanda31 Dec 2022 19:55 UTC

33 points

2 comments10 min readLW link

The Feeling of Idea Scarcity

johnswentworth31 Dec 2022 17:34 UTC

246 points

22 comments5 min readLW link 1 review

Curse of knowledge and Naive realism: Bias in Evaluating AGI X-Risks

Remmelt and flandry19

31 Dec 2022 13:33 UTC

−7 points

1 comment1 min readLW link

(www.lesswrong.com)

[Question] What career advice do you give to software engineers?

Antb31 Dec 2022 12:01 UTC

15 points

4 comments1 min readLW link

[Question] Are Mixture-of-Experts Transformers More Interpretable Than Dense Transformers?

simeon_c31 Dec 2022 11:34 UTC

8 points

5 comments1 min readLW link

[Question] In which cases can ChatGPT be used as an aid for thesis or scientific paper writing?

Bob Guran31 Dec 2022 10:50 UTC

1 point

1 comment1 min readLW link