RSS

Mark Kagach

Karma: 42

Hi, I’m Mark!

I want to understand reality and greatly progress humanity, all while building trustworthy decades-long relationships and having fun.

That led me to work on AI safety. I’m online to connect with aligned people. Consider coming along :)

markkagach.com | mark@markkagach.com

Prepar­ing for Warn­ing Shots to Cat­alyze In­ter­na­tional Co­op­er­a­tion on AGI Risks

5 Jun 2026 15:49 UTC
40 points
1 comment5 min readLW link

ALE­val: Do lan­guage mod­els lie about re­ward hack­ing?

Mark Kagach15 Apr 2026 1:57 UTC
10 points
0 comments5 min readLW link