RSS

Davidmanheim

Karma: 5,075

A Defense of Work on Math­e­mat­i­cal AI Safety

DavidmanheimJul 6, 2023, 2:15 PM
28 points
13 comments3 min readLW link
(forum.effectivealtruism.org)

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

DavidmanheimJun 26, 2023, 12:52 PM
47 points
2 comments2 min readLW link
(forum.effectivealtruism.org)

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

DavidmanheimJun 1, 2023, 7:46 AM
32 points
2 comments7 min readLW link

Sys­tems that can­not be un­safe can­not be safe

DavidmanheimMay 2, 2023, 8:53 AM
62 points
27 comments2 min readLW link

Beyond a bet­ter world

DavidmanheimDec 14, 2022, 10:18 AM
14 points
7 comments4 min readLW link
(progressforum.org)

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

DavidmanheimNov 2, 2022, 12:57 PM
73 points
27 comments4 min readLW link
(twitter.com)

An­nounc­ing AISIC 2022 - the AI Safety Is­rael Con­fer­ence, Oc­to­ber 19-20

DavidmanheimSep 21, 2022, 7:32 PM
13 points
0 comments1 min readLW link

Re­hovot, Is­rael – ACX Mee­tups Every­where 2022

DavidmanheimAug 25, 2022, 6:01 PM
3 points
0 comments1 min readLW link

AI Gover­nance across Slow/​Fast Take­off and Easy/​Hard Align­ment spectra

DavidmanheimApr 3, 2022, 7:45 AM
27 points
6 comments3 min readLW link

Ar­gu­ments about Highly Reli­able Agent De­signs as a Use­ful Path to Ar­tifi­cial In­tel­li­gence Safety

Jan 27, 2022, 1:13 PM
27 points
0 comments1 min readLW link
(arxiv.org)

Elic­i­ta­tion for Model­ing Trans­for­ma­tive AI Risks

DavidmanheimDec 16, 2021, 3:24 PM
30 points
3 comments9 min readLW link

Model­ling Trans­for­ma­tive AI Risks (MTAIR) Pro­ject: Introduction

Aug 16, 2021, 7:12 AM
91 points
0 comments9 min readLW link

Maybe An­tivirals aren’t a Use­ful Pri­or­ity for Pan­demics?

DavidmanheimJun 20, 2021, 10:04 AM
24 points
13 comments4 min readLW link

A Cru­civer­bal­ist’s In­tro­duc­tion to Bayesian reasoning

DavidmanheimApr 4, 2021, 8:50 AM
11 points
3 comments9 min readLW link

Sys­tem­atiz­ing Epistemics: Prin­ci­ples for Re­solv­ing Forecasts

DavidmanheimMar 29, 2021, 8:46 PM
33 points
8 comments11 min readLW link

Re­s­olu­tions to the Challenge of Re­solv­ing Forecasts

DavidmanheimMar 11, 2021, 7:08 PM
58 points
13 comments6 min readLW link

The Up­per Limit of Value

DavidmanheimJan 27, 2021, 2:13 PM
40 points
25 comments3 min readLW link1 review

Mul­ti­tudi­nous out­side views

DavidmanheimAug 18, 2020, 6:21 AM
55 points
13 comments3 min readLW link

Up­date more slowly!

DavidmanheimJul 13, 2020, 7:10 AM
51 points
4 comments2 min readLW link

A Per­sonal (In­terim) COVID-19 Postmortem

DavidmanheimJun 25, 2020, 6:10 PM
163 points
41 comments9 min readLW link1 review