RSS

Davidmanheim

Karma: 4,594

A Per­sonal (In­terim) COVID-19 Postmortem

Davidmanheim25 Jun 2020 18:10 UTC
163 points
41 comments9 min readLW link1 review

A Dozen Ways to Get More Dakka

Davidmanheim8 Apr 2024 4:45 UTC
127 points
10 comments3 min readLW link

Model­ling Trans­for­ma­tive AI Risks (MTAIR) Pro­ject: Introduction

Davidmanheim and Aryeh Englander
16 Aug 2021 7:12 UTC
91 points
0 comments9 min readLW link

Public Call for In­ter­est in Math­e­mat­i­cal Alignment

Davidmanheim22 Nov 2023 13:22 UTC
89 points
9 comments1 min readLW link

Far-UVC Light Up­date: No, LEDs are not around the cor­ner (tweet­storm)

Davidmanheim2 Nov 2022 12:57 UTC
71 points
27 comments4 min readLW link
(twitter.com)

Sys­tems that can­not be un­safe can­not be safe

Davidmanheim2 May 2023 8:53 UTC
62 points
27 comments2 min readLW link

Re­s­olu­tions to the Challenge of Re­solv­ing Forecasts

Davidmanheim11 Mar 2021 19:08 UTC
58 points
13 comments5 min readLW link

AI Is Not Software

Davidmanheim2 Jan 2024 7:58 UTC
56 points
29 comments5 min readLW link

Mul­ti­tudi­nous out­side views

Davidmanheim18 Aug 2020 6:21 UTC
55 points
13 comments3 min readLW link

Safe Sta­sis Fallacy

Davidmanheim5 Feb 2024 10:54 UTC
54 points
2 comments1 min readLW link

Up­date more slowly!

Davidmanheim13 Jul 2020 7:10 UTC
51 points
4 comments2 min readLW link

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

Davidmanheim15 Jul 2024 5:50 UTC
48 points
2 comments3 min readLW link

“Safety Cul­ture for AI” is im­por­tant, but isn’t go­ing to be easy

Davidmanheim26 Jun 2023 12:52 UTC
47 points
2 comments2 min readLW link
(forum.effectivealtruism.org)

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

Davidmanheim and abramdemski
13 Feb 2024 13:37 UTC
40 points
10 comments8 min readLW link

The Up­per Limit of Value

Davidmanheim27 Jan 2021 14:13 UTC
40 points
25 comments3 min readLW link1 review

Values Weren’t Com­plex, Once.

Davidmanheim25 Nov 2018 9:17 UTC
36 points
13 comments2 min readLW link

Po­ten­tial High-Lev­er­age and In­ex­pen­sive Miti­ga­tions (which are still fea­si­ble) for Pandemics

Davidmanheim9 Mar 2020 6:59 UTC
34 points
1 comment2 min readLW link

Sys­tem­atiz­ing Epistemics: Prin­ci­ples for Re­solv­ing Forecasts

Davidmanheim29 Mar 2021 20:46 UTC
33 points
8 comments11 min readLW link

“LLMs Don’t Have a Co­her­ent Model of the World”—What it Means, Why it Mat­ters

Davidmanheim1 Jun 2023 7:46 UTC
31 points
2 comments7 min readLW link

Re-in­tro­duc­ing Selec­tion vs Con­trol for Op­ti­miza­tion (Op­ti­miz­ing and Good­hart Effects—Clar­ify­ing Thoughts, Part 1)

Davidmanheim2 Jul 2019 15:36 UTC
31 points
5 comments4 min readLW link