pith. sign in

Mikita Balesni

Identifiers

  • name variant Mikita Balesni 0.60 · backfill

Papers (2)

  1. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety cs.AI · 2025 · author #2
  2. Frontier Models are Capable of In-context Scheming cs.AI · 2024 · author #4

Mentions

  • 2507.11473 #2 · arxiv_oai · confidence 0.70 Mikita Balesni
  • 2412.04984 #4 · arxiv_oai · confidence 0.70 Mikita Balesni

Frequent Coauthors