MadHatter

Karma: 359

“We are computer scientists. We do not lack in faith.” (Ketan Mulmuley)

Whither Prison Abolition?

MadHatterDec 8, 2023, 5:27 AM

−7 points

0 comments16 min readLW link

(bittertruths.substack.com)

MadHatter’s Shortform

MadHatterDec 1, 2023, 4:09 AM

4 points

3 comments LW link

A Proposed Cure for Alzheimer’s Disease???

MadHatterNov 30, 2023, 5:37 PM

4 points

30 comments2 min readLW link

A Formula for Violence (and Its Antidote)

MadHatterNov 30, 2023, 4:04 PM

−22 points

6 comments1 min readLW link

(blog.simpleheart.org)

Enkrateia: a safe model-based reinforcement learning algorithm

MadHatterNov 30, 2023, 3:51 PM

−15 points

4 comments2 min readLW link

(github.com)

Some Intuitions for the Ethicophysics

MadHatter and mishka

Nov 30, 2023, 6:47 AM

2 points

4 comments8 min readLW link

The Alignment Agenda THEY Don’t Want You to Know About

MadHatterNov 30, 2023, 4:29 AM

−19 points

16 comments1 min readLW link

Homework Answer: Glicko Ratings for War

MadHatterNov 30, 2023, 4:08 AM

−45 points

1 comment77 min readLW link

(gist.github.com)

[Question] Feature Request for LessWrong

MadHatterNov 30, 2023, 3:19 AM

11 points

8 comments1 min readLW link

My Alignment Research Agenda (“the Ethicophysics”)

MadHatterNov 30, 2023, 2:57 AM

−13 points

0 comments1 min readLW link

[Question] Stupid Question: Why am I getting consistently downvoted?

MadHatterNov 30, 2023, 12:21 AM

31 points

138 comments1 min readLW link

Ethicophysics II: Politics is the Mind-Savior

MadHatterNov 28, 2023, 4:27 PM

−9 points

9 comments4 min readLW link

(bittertruths.substack.com)

Ethicophysics I

MadHatterNov 27, 2023, 3:44 PM

−1 points

16 comments1 min readLW link

(open.substack.com)

My Mental Model of Infohazards

MadHatterNov 23, 2023, 2:37 AM

8 points

34 comments2 min readLW link 1 review

Letter to a Sonoma County Jail Cell

MadHatterNov 18, 2023, 2:24 AM

9 points

1 comment1 min readLW link

(open.substack.com)

We are Peacecraft.ai!

MadHatterNov 16, 2023, 2:15 PM

15 points

20 comments2 min readLW link

The Snuggle/Date/Slap Protocol

MadHatterNov 12, 2023, 8:44 PM

−21 points

4 comments2 min readLW link

Askesis: a model of the cerebellum

MadHatterNov 6, 2023, 8:19 PM

7 points

2 comments1 min readLW link

(github.com)

LQPR: An Algorithm for Reinforcement Learning with Provable Safety Guarantees

MadHatterNov 6, 2023, 8:17 PM

6 points

0 comments1 min readLW link

(github.com)

Balancing Security Mindset with Collaborative Research: A Proposal

MadHatterNov 1, 2023, 12:46 AM

9 points

3 comments4 min readLW link