RSS

Andrii Shportko

Karma: 16

NLAs miss some in­ter­nal­ized behaviors

8 Oct 2026 6:41 UTC
7 points
1 comment3 min readLW link

Im­mun­odefi­ciency to Par­a­sitic AI

Andrii Shportko24 Dec 2025 0:17 UTC
4 points
1 comment2 min readLW link

Low-re­sourced lan­guages get jailbro­ken more. Can SAEs ex­plain why?

Andrii Shportko16 Sep 2025 5:51 UTC
9 points
1 comment3 min readLW link