RSS

Davidmanheim

Karma: 5,112

Ther­a­pist in the Weights: Risks of Hyper-In­tro­spec­tion in Fu­ture AI Systems

DavidmanheimApr 28, 2025, 6:42 AM
15 points
1 comment5 min readLW link

Grounded Ghosts in the Ma­chine—Fris­ton Blan­kets, Mir­ror Neu­rons, and the Quest for Co­op­er­a­tive AI

DavidmanheimApr 10, 2025, 10:15 AM
9 points
0 comments9 min readLW link
(davidmanheim.com)

David­man­heim’s Shortform

DavidmanheimJan 16, 2025, 8:23 AM
7 points
18 commentsLW link

Ex­plor­ing Co­op­er­a­tion: The Path to Utopia

DavidmanheimDec 25, 2024, 6:31 PM
11 points
0 commentsLW link
(exploringcooperation.substack.com)

Moder­ately Skep­ti­cal of “Risks of Mir­ror Biol­ogy”

DavidmanheimDec 20, 2024, 12:57 PM
32 points
3 comments9 min readLW link
(substack.com)

Most Minds are Irrational

DavidmanheimDec 10, 2024, 9:36 AM
17 points
4 comments10 min readLW link

Re­fut­ing Searle’s wall, Put­nam’s rock, and John­son’s popcorn

DavidmanheimDec 9, 2024, 8:24 AM
9 points
31 comments1 min readLW link

Miti­gat­ing Geo­mag­netic Storm and EMP Risks to the Elec­tri­cal Grid (Shal­low Dive)

DavidmanheimNov 26, 2024, 8:00 AM
16 points
4 comments6 min readLW link

Prove­ably Safe Self Driv­ing Cars [Mo­dulo As­sump­tions]

DavidmanheimSep 15, 2024, 1:58 PM
27 points
29 comments8 min readLW link

Are LLMs on the Path to AGI?

DavidmanheimAug 30, 2024, 3:14 AM
14 points
2 comments5 min readLW link

Scal­ing Laws and Likely Limits to AI

DavidmanheimAug 18, 2024, 5:19 PM
19 points
0 commentsLW link

Mis­nam­ing and Other Is­sues with OpenAI’s “Hu­man Level” Su­per­in­tel­li­gence Hierarchy

DavidmanheimJul 15, 2024, 5:50 AM
49 points
2 comments3 min readLW link

Biorisk is an Un­helpful Anal­ogy for AI Risk

DavidmanheimMay 6, 2024, 6:20 AM
4 points
17 commentsLW link

A Dozen Ways to Get More Dakka

DavidmanheimApr 8, 2024, 4:45 AM
133 points
11 comments3 min readLW link

“Open Source AI” isn’t Open Source

DavidmanheimFeb 15, 2024, 8:59 AM
18 points
16 comments1 min readLW link
(davidmanheim.substack.com)

Tech­nolo­gies and Ter­minol­ogy: AI isn’t Soft­ware, it’s… Deep­ware?

Davidmanheim and abramdemski
Feb 13, 2024, 1:37 PM
40 points
10 comments8 min readLW link

Safe Sta­sis Fallacy

DavidmanheimFeb 5, 2024, 10:54 AM
54 points
2 commentsLW link

AI Is Not Software

DavidmanheimJan 2, 2024, 7:58 AM
58 points
29 comments5 min readLW link

Public Call for In­ter­est in Math­e­mat­i­cal Alignment

DavidmanheimNov 22, 2023, 1:22 PM
90 points
9 comments1 min readLW link

What is au­ton­omy, and how does it lead to greater risk from AI?

DavidmanheimAug 1, 2023, 7:58 AM
30 points
0 comments6 min readLW link