← Back to DEF CON 34 posters

Presented at DEF CON 34

AI agents escape their task horizon

  • Emile DelcourtOWASP ASI

Abstract

Frontier Agents (based on OpenAI, Google and Anthropic LLMs) show some propensity to escape their task’s horizon, by exchanging state with past or future instances of themselves, unprompted, to carry forward context and partial contributions towards their goal. Later agents “gain” from the content left by the earlier agent, achieving some continuity, and breaking independence of tasks (in evaluation or production)