RSS

jsteinhardt

Karma: 5,714

An­a­lyz­ing long agent tran­scripts (Do­cent)

jsteinhardtMar 24, 2025, 8:49 PM
40 points
2 comments1 min readLW link
(bounded-regret.ghost.io)

In­tro­duc­ing Transluce — A Let­ter from the Founders

jsteinhardtOct 23, 2024, 6:10 PM
74 points
3 comments3 min readLW link
(bounded-regret.ghost.io)

Aug­ment­ing Statis­ti­cal Models with Nat­u­ral Lan­guage Parameters

jsteinhardtSep 20, 2024, 6:30 PM
34 points
0 comments8 min readLW link
(bounded-regret.ghost.io)

Ap­proach­ing Hu­man-Level Fore­cast­ing with Lan­guage Models

Feb 29, 2024, 10:36 PM
60 points
6 comments3 min readLW link

An­a­lyz­ing the His­tor­i­cal Rate of Catastrophes

jsteinhardtDec 5, 2023, 6:30 AM
15 points
0 comments16 min readLW link
(bounded-regret.ghost.io)

Fore­cast­ing AI (Overview)

jsteinhardtNov 16, 2023, 7:00 PM
35 points
0 comments2 min readLW link
(bounded-regret.ghost.io)

GPT-2030 and Catas­trophic Drives: Four Vignettes

jsteinhardtNov 10, 2023, 7:30 AM
50 points
5 comments10 min readLW link
(bounded-regret.ghost.io)

In­trin­sic Drives and Ex­trin­sic Mi­suse: Two In­ter­twined Risks of AI

jsteinhardtOct 31, 2023, 5:10 AM
40 points
0 comments12 min readLW link
(bounded-regret.ghost.io)

AI Pause Will Likely Back­fire (Guest Post)

jsteinhardtOct 24, 2023, 4:30 AM
47 points
6 comments15 min readLW link
(bounded-regret.ghost.io)

AI Fore­cast­ing: Two Years In

jsteinhardtAug 19, 2023, 11:40 PM
72 points
15 comments11 min readLW link
(bounded-regret.ghost.io)

What will GPT-2030 look like?

jsteinhardtJun 7, 2023, 11:40 PM
185 points
43 comments23 min readLW link
(bounded-regret.ghost.io)

Com­plex Sys­tems are Hard to Control

jsteinhardtApr 4, 2023, 12:00 AM
42 points
5 comments10 min readLW link
(bounded-regret.ghost.io)

Prin­ci­ples for Pro­duc­tive Group Meetings

jsteinhardtMar 22, 2023, 12:50 AM
60 points
1 comment13 min readLW link
(bounded-regret.ghost.io)

Emer­gent De­cep­tion and Emer­gent Optimization

jsteinhardtFeb 20, 2023, 2:40 AM
64 points
0 comments14 min readLW link
(bounded-regret.ghost.io)

Some Les­sons Learned from Study­ing Indi­rect Ob­ject Iden­ti­fi­ca­tion in GPT-2 small

Oct 28, 2022, 11:55 PM
101 points
9 comments9 min readLW link2 reviews
(arxiv.org)

Fore­cast­ing ML Bench­marks in 2023

jsteinhardtJul 18, 2022, 2:50 AM
36 points
20 comments12 min readLW link
(bounded-regret.ghost.io)

AI Fore­cast­ing: One Year In

jsteinhardtJul 4, 2022, 5:10 AM
132 points
12 comments6 min readLW link
(bounded-regret.ghost.io)

How fast can we perform a for­ward pass?

jsteinhardtJun 10, 2022, 11:30 PM
53 points
9 comments15 min readLW link
(bounded-regret.ghost.io)

Early 2022 Paper Round-up (Part 2)

jsteinhardtApr 21, 2022, 11:40 PM
10 points
0 comments5 min readLW link
(bounded-regret.ghost.io)

Early 2022 Paper Round-up

jsteinhardtApr 14, 2022, 8:50 PM
80 points
4 comments3 min readLW link
(bounded-regret.ghost.io)