RSS

Shoshannah Tekofsky

Karma: 624

Naive Hy­pothe­ses on AI Alignment

Shoshannah Tekofsky2 Jul 2022 19:03 UTC
98 points
29 comments5 min readLW link

Re­search Notes: What are we al­ign­ing for?

Shoshannah Tekofsky8 Jul 2022 22:13 UTC
19 points
8 comments2 min readLW link

Align­ment as Game Design

Shoshannah Tekofsky16 Jul 2022 22:36 UTC
11 points
7 comments2 min readLW link

Cul­ti­vat­ing Valiance

Shoshannah Tekofsky13 Aug 2022 18:47 UTC
35 points
4 comments4 min readLW link

Novelty Gen­er­a­tion—The Art of Good Ideas

Shoshannah Tekofsky20 Aug 2022 0:36 UTC
15 points
2 comments9 min readLW link

Over­ton Gym­nas­tics: An Ex­er­cise in Discomfort

5 Sep 2022 19:20 UTC
40 points
15 comments4 min readLW link

Let’s Com­pare Notes

Shoshannah Tekofsky22 Sep 2022 20:47 UTC
17 points
3 comments6 min readLW link

Dep­re­cated: Some hu­mans are fit­ness maximizers

Shoshannah Tekofsky4 Oct 2022 19:38 UTC
6 points
22 comments6 min readLW link

Three Align­ment Schemas & Their Problems

Shoshannah Tekofsky26 Nov 2022 4:25 UTC
19 points
1 comment6 min readLW link

Re­search Prin­ci­ples for 6 Months of AI Align­ment Studies

Shoshannah Tekofsky2 Dec 2022 22:55 UTC
23 points
3 comments6 min readLW link

Loose Threads on Intelligence

Shoshannah Tekofsky24 Dec 2022 0:38 UTC
11 points
3 comments8 min readLW link

An­nounc­ing: The In­de­pen­dent AI Safety Registry

Shoshannah Tekofsky26 Dec 2022 21:22 UTC
53 points
9 comments1 min readLW link

Op­ti­miz­ing Hu­man Col­lec­tive In­tel­li­gence to Align AI

Shoshannah Tekofsky7 Jan 2023 1:21 UTC
12 points
5 comments6 min readLW link

A Sim­ple Align­ment Typology

Shoshannah Tekofsky28 Jan 2023 5:26 UTC
34 points
2 comments2 min readLW link

Reflec­tions on De­cep­tion & Gen­er­al­ity in Scal­able Over­sight (Another OpenAI Align­ment Re­view)

Shoshannah Tekofsky28 Jan 2023 5:26 UTC
53 points
7 comments7 min readLW link

Short Notes on Re­search Process

Shoshannah Tekofsky22 Feb 2023 23:41 UTC
21 points
0 comments2 min readLW link

United We Align: Har­ness­ing Col­lec­tive Hu­man In­tel­li­gence for AI Align­ment Progress

Shoshannah Tekofsky20 Apr 2023 23:19 UTC
41 points
13 comments25 min readLW link

Pre­dict­ing Align­ment Award Win­ners Us­ing ChatGPT 4

Shoshannah Tekofsky8 Feb 2024 14:38 UTC
16 points
2 comments11 min readLW link