Experiments

Tag

Self-Blinded Caffeine RCT

niplav27 Jun 2023 12:38 UTC

45 points

9 comments8 min readLW link

[Part 1] Amplifying generalist research via forecasting – Models of impact and challenges

Bird Concept, ozziegooen, Elizabeth, NunoSempere and Ben Goldhaber

19 Dec 2019 15:50 UTC

55 points

29 comments17 min readLW link

Notifications Received in 30 Minutes of Class

tanagrabeast26 May 2024 17:02 UTC

373 points

17 comments8 min readLW link 1 review

Scientific Wrestling: Beyond Passive Hypothesis-Testing

adamShimi7 Mar 2022 12:01 UTC

44 points

6 comments8 min readLW link

Randomized Zettelkasten Test

Josephine21 Jul 2021 17:21 UTC

32 points

7 comments7 min readLW link

Self-Blinded L-Theanine RCT

niplav31 Oct 2023 15:24 UTC

53 points

12 comments3 min readLW link

Michael Dickens’ Caffeine Tolerance Research

niplav4 Sep 2024 15:41 UTC

47 points

5 comments2 min readLW link

(mdickens.me)

Should I buy roofies from the darknet?

Malmesbury22 Apr 2022 15:40 UTC

14 points

4 comments3 min readLW link

Extrapolating from Five Words

Gordon Seidoh Worley15 Nov 2023 23:21 UTC

40 points

11 comments2 min readLW link

[April Fools’] Definitive confirmation of shard theory

TurnTrout1 Apr 2023 7:27 UTC

170 points

8 comments2 min readLW link

Long Covid Informal Study Results

Elizabeth16 Oct 2021 7:10 UTC

43 points

3 comments5 min readLW link

(acesounderglass.com)

Pasta Cooking Time

jefftk23 Aug 2025 3:00 UTC

22 points

1 comment1 min readLW link

(www.jefftk.com)

Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir and JacksonKaunismaa

6 Aug 2024 17:44 UTC

31 points

0 comments2 min readLW link

0.836 Bits of Evidence In Favor of Futarchy

niplav and Claude+

29 Sep 2024 21:57 UTC

38 points

0 comments3 min readLW link

Positly covid survey 2: controlled productivity data

KatjaGrace4 Feb 2022 7:30 UTC

15 points

1 comment4 min readLW link

(worldspiritsockpuppet.com)

A Cheaper Way to Test Ventilation Rates?

casualphysicsenjoyer17 Sep 2025 21:10 UTC

18 points

1 comment4 min readLW link

(chillphysicsenjoyer.substack.com)

Self-Experiment: Does Working More Hours Increase My Output?

lynettebye3 Apr 2020 21:36 UTC

54 points

0 comments4 min readLW link

Please Bet On My Quantified Self Decision Markets

niplav1 Dec 2023 20:07 UTC

36 points

6 comments6 min readLW link

Pomodoro Method Randomized Self Experiment

niplav29 Sep 2024 21:55 UTC

16 points

2 comments1 min readLW link

Loose thoughts on AGI risk

Yitz23 Jun 2022 1:02 UTC

7 points

3 comments1 min readLW link

My hour of memoryless lucidity

Eric Neyman4 May 2024 1:40 UTC

380 points

38 comments5 min readLW link 1 review

(ericneyman.wordpress.com)

Increasing IQ by 10 Points is Possible

George3d619 Mar 2024 20:48 UTC

24 points

51 comments5 min readLW link

(morelucid.substack.com)

Rationality Market Research

Raemon14 Jul 2011 19:41 UTC

79 points

86 comments7 min readLW link

Hyperpalatable Food Hypothesis: A LessWrong Study?

BDay23 Jan 2022 5:43 UTC

23 points

33 comments1 min readLW link

Shorter Tokens Are More Likely

Brendan Long24 Aug 2025 0:22 UTC

101 points

19 comments5 min readLW link

(www.brendanlong.com)

Rationality and playfulness

DirectedEvolution12 Sep 2020 5:14 UTC

42 points

1 comment11 min readLW link

Friedman’s “Prediction vs. Explanation”

Eliezer Yudkowsky29 Sep 2008 6:15 UTC

9 points

79 comments1 min readLW link

Untitled Draft

Михаил Захарченко26 May 2025 17:12 UTC

1 point

0 comments2 min readLW link

Experiment: a good researcher is hard to find

gwern30 Apr 2012 17:13 UTC

53 points

20 comments2 min readLW link

Participating in a Covid-19 Vaccine Trial

ejacob11 Feb 2021 20:35 UTC

37 points

14 comments7 min readLW link

(eidan.substack.com)

[Paper] Hidden in Plain Text: Emergence and Mitigation of Steganographic Collusion in LLMs

Yohan Mathew, joanv, robert mccarthy, ollie, Nandi and Dylan Cope

25 Sep 2024 14:52 UTC

37 points

2 comments4 min readLW link

(arxiv.org)

Claude wants to be conscious

Joe Kwon13 Apr 2024 1:40 UTC

2 points

8 comments6 min readLW link

A Block-Based Regularization Proposal for Neural Networks

Otto.Dev19 Apr 2025 18:56 UTC

−8 points

0 comments1 min readLW link

Better thinking through experiential games

Morendil23 Oct 2009 12:59 UTC

39 points

36 comments3 min readLW link

Experiment: Test your priors on Bernoulli processes.

joseph_c12 Oct 2025 22:09 UTC

20 points

15 comments1 min readLW link

Does GPT-4 exhibit agency when summarizing articles?

Christopher King24 Mar 2023 15:49 UTC

16 points

2 comments5 min readLW link

Solving Math Problems by Relay

Ben Goldhaber and Owain_Evans

17 Jul 2020 15:32 UTC

112 points

26 comments7 min readLW link

Participating in a Covid-19 Vaccine Trial #3: I Hope I feel Worse Tomorrow

ejacob5 Mar 2021 0:02 UTC

8 points

2 comments5 min readLW link

LLM Self-Reference Language in Multilingual vs English-Centric Models

dwmd22 Oct 2025 12:44 UTC

4 points

0 comments6 min readLW link

[link]Mass replication of Psychology articles planed.

beoShaffer18 Apr 2012 16:13 UTC

41 points

8 comments1 min readLW link

Using math to foster acceptance and equality

jackoda5 Nov 2025 5:16 UTC

−1 points

0 comments1 min readLW link

Split Personality Training: Revealing Latent Knowledge Through Personality-Shift Tokens

Florian_Dietz10 Mar 2025 16:07 UTC

44 points

7 comments9 min readLW link

[Question] Do You Have an Internal Monologue?

belkarx9 Dec 2022 3:04 UTC

23 points

7 comments1 min readLW link

Memorizing a Deck of Cards

Tofly16 Sep 2020 1:31 UTC

27 points

1 comment2 min readLW link

Experimental longtermism: theory needs data

Jan_Kulveit and technicalities

24 Mar 2022 8:23 UTC

52 points

0 comments4 min readLW link

(forum.effectivealtruism.org)

Go flash blinking lights at printed text right now

lemonhope5 Nov 2023 7:29 UTC

15 points

9 comments1 min readLW link

More experiments in GPT-4 agency: writing memos

Christopher King24 Mar 2023 17:51 UTC

5 points

2 comments10 min readLW link

Exploring OpenAI’s Latent Directions: Tests, Observations, and Poking Around

Johnny Lin31 Jan 2024 6:01 UTC

26 points

4 comments14 min readLW link

Air Conditioner Test Results & Discussion

johnswentworth22 Jun 2022 22:26 UTC

82 points

42 comments6 min readLW link

Gradient Anatomy’s—Hallucination Robustness in Medical Q&A

DieSab12 Feb 2025 19:16 UTC

2 points

0 comments10 min readLW link

Results of “Experiment on Bernoulli processes”

joseph_c26 Oct 2025 21:47 UTC

9 points

2 comments4 min readLW link

Notes on an Experiment with Markets

Jeffrey Heninger23 Nov 2022 16:10 UTC

8 points

0 comments4 min readLW link

(aiimpacts.org)

Experiment Idea Thread - Spring 2011

Psychohistorian6 May 2011 18:10 UTC

35 points

54 comments1 min readLW link

Who Feels More Alone?

marvinscheffold22 Sep 2024 11:54 UTC

−8 points

2 comments39 min readLW link

Why I’m Pouring Cold Water in My Left Ear, and You Should Too

Maloew24 Jan 2025 23:13 UTC

12 points

0 comments2 min readLW link

Early Experiments in Human Auditing for AI Control

Joey Yudelson and Buck

23 Jan 2025 1:34 UTC

28 points

1 comment7 min readLW link

Experiments and Consent

jefftk10 Nov 2019 14:50 UTC

30 points

45 comments1 min readLW link

(www.jefftk.com)

Simple experiments with deceptive alignment

Andreas_Moe15 May 2023 17:41 UTC

7 points

0 comments4 min readLW link

Some negative steganography results

Fabien Roger9 Dec 2023 20:22 UTC

60 points

5 comments2 min readLW link

Ten experiments in modularity, which we’d like you to run!

CallumMcDougall, Lucius Bushnaq and Avery

16 Jun 2022 9:17 UTC

62 points

3 comments9 min readLW link

Existentially relevant thought experiment: To kill or not to kill, a sniper, a man and a button.

AlexFromSafeTransition14 Aug 2023 10:53 UTC

−18 points

6 comments4 min readLW link

The need for multi-agent experiments

Martín Soto1 Aug 2024 17:14 UTC

43 points

3 comments9 min readLW link

Minimal Prompt Induction of Self-Talk in Base LLMs

dwmd15 Oct 2025 1:15 UTC

2 points

0 comments5 min readLW link

Smoke without fire is scary

Adam Jermyn4 Oct 2022 21:08 UTC

52 points

22 comments4 min readLW link

A Proposal for Evolving AI Alignment Through Computational Homeostasis

Derek Chisholm20 Aug 2025 17:43 UTC

1 point

0 comments3 min readLW link

[Question] Has Someone Checked The Cold-Water-In-Left-Ear Thing?

Maloew28 Dec 2024 20:15 UTC

11 points

0 comments1 min readLW link

A Symbolic Model for Recursive Interpretation and Containment in LLMs

Desjuan13 Jul 2025 19:33 UTC

1 point

0 comments1 min readLW link

Preregistration: Air Conditioner Test

johnswentworth21 Apr 2022 19:48 UTC

112 points

59 comments7 min readLW link

Self-experiment Protocol: Effect of Chocolate on Sleep

NoSignalNoNoise22 Jul 2019 3:32 UTC

30 points

8 comments2 min readLW link

No comments.