zeshen

Karma: 410

Feedback welcomed: www.admonymous.co/zeshen

I sometimes write my thoughts here: airisks.substack.com

zeshen’s Shortform

zeshen17 Feb 2026 6:46 UTC

4 points

2 comments1 min readLW link

On thinking about AI risks concretely

zeshen11 Jul 2025 0:04 UTC

9 points

4 comments4 min readLW link

Non-loss of control AGI-related catastrophes are out of control too

Yi-Yang, Mo Putera and zeshen

12 Jun 2023 12:01 UTC

2 points

3 comments24 min readLW link

[Question] Is there a way to sort LW search results by date posted?

zeshen12 Mar 2023 4:56 UTC

5 points

1 comment1 min readLW link

A newcomer’s guide to the technical AI safety field

zeshen4 Nov 2022 14:29 UTC

43 points

3 comments10 min readLW link

Embedding safety in ML development

zeshen31 Oct 2022 12:27 UTC

24 points

1 comment18 min readLW link

aisafety.community—A living document of AI safety communities

zeshen and plex

28 Oct 2022 17:50 UTC

58 points

23 comments1 min readLW link

My Thoughts on the ML Safety Course

zeshen27 Sep 2022 13:15 UTC

50 points

3 comments17 min readLW link

Summary of ML Safety Course

zeshen27 Sep 2022 13:05 UTC

7 points

0 comments6 min readLW link

Levels of goals and alignment

zeshen16 Sep 2022 16:44 UTC

27 points

4 comments6 min readLW link

What if we approach AI safety like a technical engineering safety problem

zeshen20 Aug 2022 10:29 UTC

36 points

4 comments7 min readLW link

I missed the crux of the alignment problem the whole time

zeshen13 Aug 2022 10:11 UTC

53 points

7 comments3 min readLW link