Vasily Konovalov's picture

2 15

Vasily Konovalov

Vasily

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 19 days ago

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

authored a paper 21 days ago

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

upvoted a paper 22 days ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

View all activity

Organizations

Vasily 's models 2

Vasily/reduce

Updated Mar 11, 2022 • 2

Vasily/match

Updated Mar 11, 2022