Mikhail Salnikov's picture

6 14 1

Mikhail Salnikov

msalnikov

·

mdsalnikov

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

upvoted a paper 15 days ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

upvoted a paper about 2 months ago

<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs

View all activity

Organizations

msalnikov 's models

None public yet