Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Davidmanheim
Karma:
5,075
All
Posts
Comments
New
Top
Old
Page
1
Therapist in the Weights: Risks of Hyper-Introspection in Future AI Systems
Davidmanheim
Apr 28, 2025, 6:42 AM
15
points
1
comment
5
min read
LW
link
Grounded Ghosts in the Machine—Friston Blankets, Mirror Neurons, and the Quest for Cooperative AI
Davidmanheim
Apr 10, 2025, 10:15 AM
9
points
0
comments
9
min read
LW
link
(davidmanheim.com)
Davidmanheim’s Shortform
Davidmanheim
Jan 16, 2025, 8:23 AM
7
points
18
comments
LW
link
Exploring Cooperation: The Path to Utopia
Davidmanheim
Dec 25, 2024, 6:31 PM
11
points
0
comments
LW
link
(exploringcooperation.substack.com)
Moderately Skeptical of “Risks of Mirror Biology”
Davidmanheim
Dec 20, 2024, 12:57 PM
32
points
3
comments
9
min read
LW
link
(substack.com)
Most Minds are Irrational
Davidmanheim
Dec 10, 2024, 9:36 AM
17
points
4
comments
10
min read
LW
link
Refuting Searle’s wall, Putnam’s rock, and Johnson’s popcorn
Davidmanheim
Dec 9, 2024, 8:24 AM
9
points
31
comments
1
min read
LW
link
Mitigating Geomagnetic Storm and EMP Risks to the Electrical Grid (Shallow Dive)
Davidmanheim
Nov 26, 2024, 8:00 AM
16
points
4
comments
6
min read
LW
link
Proveably Safe Self Driving Cars [Modulo Assumptions]
Davidmanheim
Sep 15, 2024, 1:58 PM
27
points
29
comments
8
min read
LW
link
Are LLMs on the Path to AGI?
Davidmanheim
Aug 30, 2024, 3:14 AM
14
points
2
comments
5
min read
LW
link
Scaling Laws and Likely Limits to AI
Davidmanheim
Aug 18, 2024, 5:19 PM
19
points
0
comments
LW
link
Misnaming and Other Issues with OpenAI’s “Human Level” Superintelligence Hierarchy
Davidmanheim
Jul 15, 2024, 5:50 AM
48
points
2
comments
3
min read
LW
link
Biorisk is an Unhelpful Analogy for AI Risk
Davidmanheim
May 6, 2024, 6:20 AM
4
points
17
comments
LW
link
A Dozen Ways to Get More Dakka
Davidmanheim
Apr 8, 2024, 4:45 AM
132
points
11
comments
3
min read
LW
link
“Open Source AI” isn’t Open Source
Davidmanheim
Feb 15, 2024, 8:59 AM
18
points
16
comments
1
min read
LW
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
comments
8
min read
LW
link
Safe Stasis Fallacy
Davidmanheim
5 Feb 2024 10:54 UTC
54
points
2
comments
LW
link
AI Is Not Software
Davidmanheim
2 Jan 2024 7:58 UTC
58
points
29
comments
5
min read
LW
link
Public Call for Interest in Mathematical Alignment
Davidmanheim
22 Nov 2023 13:22 UTC
90
points
9
comments
1
min read
LW
link
What is autonomy, and how does it lead to greater risk from AI?
Davidmanheim
1 Aug 2023 7:58 UTC
30
points
0
comments
6
min read
LW
link
Back to top
Next