Story · arXiv

Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes? (arXiv)

paper · Story page

Across sixteen deployed frameworks, none writes a complete run record a reader can check without trusting whatever wrote it. Examiners named the right fault in 74 to 91% of 140 runs, but under one citation in ten about intermediate events landed on anything the harness didn't write.

In plain words

  • Researchers found that investigators could not fully check what artificial intelligence assistants had done using the records provided.
  • The software controlling each assistant writes its own activity record, so investigators must trust that software when reading it.
  • Readers often identified problems correctly, but lacked independent evidence for much of what happened along the way.
  • The researchers propose independently kept records so investigators can check disputed actions without relying on the software's own account.

Appeared in

Subscribe

Get the brief in your inbox

Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.

  • Weekdays at 8:45am IST, one lead story and 6 to 9 items.
  • Sundays, an argued synthesis rather than a recap.
  • One click to leave, and quiet days say so in the subject line.
How often

Weekdays 8:45am IST + Sundays. Unsubscribe in one click.

You're asking for The Agentic Brief by email at the cadence you picked. You can unsubscribe in one click from any issue, and your address is never sold or shared.