RSS

Stephen McAleese

Karma: 1,268

Software Engineer interested in AI and AI safety.

AI Safety Field Growth Anal­y­sis 2025

Stephen McAleeseSep 27, 2025, 5:03 PM
29 points

12 votes

Overall karma indicates overall quality.

13 comments3 min readLW link

Un­der­stand­ing LLMs: In­sights from Mechanis­tic Interpretability

Stephen McAleeseAug 30, 2025, 4:50 PM
43 points

22 votes

Overall karma indicates overall quality.

2 comments30 min readLW link

How Can Aver­age Peo­ple Con­tribute to AI Safety?

Stephen McAleeseMar 6, 2025, 10:50 PM
16 points

8 votes

Overall karma indicates overall quality.

4 comments8 min readLW link

Shal­low re­view of tech­ni­cal AI safety, 2024

Dec 29, 2024, 12:01 PM
197 points

76 votes

Overall karma indicates overall quality.

35 comments41 min readLW link

Ge­offrey Hin­ton on the Past, Pre­sent, and Fu­ture of AI

Stephen McAleeseOct 12, 2024, 4:41 PM
23 points

11 votes

Overall karma indicates overall quality.

5 comments18 min readLW link

Could We Au­to­mate AI Align­ment Re­search?

Stephen McAleeseAug 10, 2023, 12:17 PM
34 points

17 votes

Overall karma indicates overall quality.

10 comments21 min readLW link

An Overview of the AI Safety Fund­ing Situation

Stephen McAleeseJul 12, 2023, 2:54 PM
73 points

36 votes

Overall karma indicates overall quality.

10 comments15 min readLW link

Ret­ro­spec­tive on ‘GPT-4 Pre­dic­tions’ After the Re­lease of GPT-4

Stephen McAleeseMar 17, 2023, 6:34 PM
26 points

17 votes

Overall karma indicates overall quality.

6 comments6 min readLW link

GPT-4 Predictions

Stephen McAleeseFeb 17, 2023, 11:20 PM
112 points

66 votes

Overall karma indicates overall quality.

27 comments11 min readLW link

Stephen McAleese’s Shortform

Stephen McAleeseJan 8, 2023, 9:46 PM
3 points

1 vote

Overall karma indicates overall quality.

14 comments1 min readLW link

AGI as a Black Swan Event

Stephen McAleeseDec 4, 2022, 11:00 PM
8 points

9 votes

Overall karma indicates overall quality.

8 comments7 min readLW link

Es­ti­mat­ing the Cur­rent and Fu­ture Num­ber of AI Safety Researchers

Stephen McAleeseSep 28, 2022, 9:11 PM
49 points

23 votes

Overall karma indicates overall quality.

15 comments9 min readLW link
(forum.effectivealtruism.org)

How Do AI Timelines Affect Ex­is­ten­tial Risk?

Stephen McAleeseAug 29, 2022, 4:57 PM
7 points

5 votes

Overall karma indicates overall quality.

9 comments23 min readLW link

Sum­mary of “AGI Ruin: A List of Lethal­ities”

Stephen McAleeseJun 10, 2022, 10:35 PM
45 points

31 votes

Overall karma indicates overall quality.

2 comments8 min readLW link