Skip to content
Jason Ehmke
esc
  • Loading index…
↑↓ navigate↵ open

Writing

The notebook

Essays when an idea is ready, notes while it isn’t, reviews of papers worth the time, and experiments with the code attached. Each entry says how sure I am.

2026

2 entries

  • What Breaks When You Split a Job Across AI Agents

    Five AI agents worked a bank fraud case in sequence, each passing its work to the next. Giving each agent a list of fields to fill in mattered most: it raised completed cases from 17 to 49 of 60. With JSON records, a chain came close to one agent doing the whole job; with plain text, it fell well short. Chains lost details, added conditions nobody could meet, and passed along wrong conclusions no later agent could check.


    Experiment, 27 min

  • Accidental Harm From an LLM Agent: Acting Before Reading Its Tools

    LLM agents patching servers caused damage not by breaking policy but by acting before they understood their tools. A small model rebooted servers by accident in nearly half of runs; both models restarted nodes still serving traffic in 88% of rolling-cluster runs. Simple interface changes stopped the reboots.


    Experiment, 32 min

Earlier

Looking for the leadership writing? 131 essays are in the archive.