pith. sign in

Ryan Greenblatt

Identifiers

  • name variant Ryan Greenblatt 0.60 · backfill

Papers (4)

  1. Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models cs.AI · 2026 · author #20
  2. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety cs.AI · 2025 · author #14
  3. Alignment faking in large language models cs.AI · 2024 · author #1
  4. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training cs.CR · 2024 · author #36

Mentions

  • 2606.07157 #20 · arxiv_oai · confidence 0.70 Ryan Greenblatt
  • 2507.11473 #14 · arxiv_oai · confidence 0.70 Ryan Greenblatt

Frequent Coauthors