RSS

Anthony DiGiovanni

Karma: 1,329

Researcher at the Center on Long-Term Risk. All opinions my own.

An­nounc­ing the Safe Pareto Im­prove­ments (SPI) Fun­da­men­tals Program

Anthony DiGiovanni3 Jul 2026 15:55 UTC
43 points
1 comment3 min readLW link

Clue­less­ness: Sum­mary of the ar­gu­ment, why it mat­ters, and counterarguments

Anthony DiGiovanni30 Jun 2026 20:54 UTC
25 points
6 comments9 min readLW link

A high-level model of AI bargaining

Anthony DiGiovanni21 Jun 2026 15:37 UTC
24 points
1 comment5 min readLW link

[Linkpost] Evals for “SPI-in­com­pat­i­ble” be­hav­ior & rea­son­ing: Guide to ini­tial research

Anthony DiGiovanni9 Jun 2026 13:44 UTC
23 points
0 comments1 min readLW link
(docs.google.com)

CLR’s Safe Pareto Im­prove­ments Re­search Agenda

Anthony DiGiovanni20 Apr 2026 9:28 UTC
46 points
9 comments14 min readLW link

How to not do de­ci­sion the­ory backwards

Anthony DiGiovanni17 Mar 2026 7:22 UTC
20 points
1 comment16 min readLW link

When do in­tu­itions need to be re­li­able?

Anthony DiGiovanni15 Mar 2026 4:18 UTC
8 points
8 comments3 min readLW link

Re­source guide: Unaware­ness, in­de­ter­mi­nacy, and cluelessness

Anthony DiGiovanni7 Jul 2025 9:54 UTC
20 points
0 comments7 min readLW link

Clar­ify­ing “wis­dom”: Foun­da­tional top­ics for al­igned AIs to pri­ori­tize be­fore ir­re­versible decisions

Anthony DiGiovanni20 Jun 2025 21:55 UTC
42 points
2 comments12 min readLW link

4. Why ex­ist­ing ap­proaches to cause pri­ori­ti­za­tion are not ro­bust to unawareness

Anthony DiGiovanni13 Jun 2025 8:55 UTC
26 points
0 comments16 min readLW link

3. Why im­par­tial al­tru­ists should sus­pend judg­ment un­der unawareness

Anthony DiGiovanni8 Jun 2025 15:06 UTC
24 points
0 comments14 min readLW link

2. Why in­tu­itive com­par­i­sons of large-scale im­pact are unjustified

Anthony DiGiovanni4 Jun 2025 20:30 UTC
25 points
0 comments16 min readLW link

1. The challenge of un­aware­ness for im­par­tial al­tru­ist ac­tion guidance: Introduction

Anthony DiGiovanni2 Jun 2025 8:54 UTC
48 points
6 comments13 min readLW link

Should you go with your best guess?: Against pre­cise Bayesi­anism and re­lated views

Anthony DiGiovanni27 Jan 2025 20:25 UTC
67 points
16 comments22 min readLW link

Win­ning isn’t enough

JesseClifton and Anthony DiGiovanni
5 Nov 2024 11:37 UTC
44 points
35 comments9 min readLW link

[Question] What are your cruxes for im­pre­cise prob­a­bil­ities /​ de­ci­sion rules?

Anthony DiGiovanni31 Jul 2024 15:42 UTC
36 points
33 comments1 min readLW link

In­di­vi­d­u­ally in­cen­tivized safe Pareto im­prove­ments in open-source bargaining

Nicolas Macé, Anthony DiGiovanni and JesseClifton
17 Jul 2024 18:26 UTC
41 points
3 comments17 min readLW link

In defense of an­throp­i­cally up­dat­ing EDT

Anthony DiGiovanni5 Mar 2024 6:21 UTC
20 points
18 comments13 min readLW link

Mak­ing AIs less likely to be spiteful

Nicolas Macé, Anthony DiGiovanni and JesseClifton
26 Sep 2023 14:12 UTC
118 points
7 comments10 min readLW link

Re­sponses to ap­par­ent ra­tio­nal­ist con­fu­sions about game /​ de­ci­sion theory

Anthony DiGiovanni30 Aug 2023 22:02 UTC
143 points
20 comments12 min readLW link1 review