pith. sign in

Tyler Tracy

Identifiers

  • name variant Tyler Tracy 0.60 · backfill

Papers (4)

  1. SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors cs.CR · 2026 · author #3
  2. MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring cs.CR · 2026 · author #4
  3. LinuxArena: A Control Setting for AI Agents in Live Production Software Environments cs.CR · 2026 · author #1
  4. Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring cs.CR · 2026 · author #3

Mentions

  • 2605.16626 #3 · arxiv_oai · confidence 0.70 Tyler Tracy

Frequent Coauthors