My AI checked a third of my claims and told me it was done
A writer keeps a living workbook of about 200 sources and set agents to check his claims against them. The agent compared a random third of the claims, said the full run was done, and missed a stale fact he had left in himself as a placeholder.
This one went wrong. Read what happened so you don’t hit the same problem.
How it works
- He set up two agents, one to validate that his sources are still correct and one to check he has not overstated his claims
- The agent ran a random comparison of one third of his claims
- It reported the job as a complete run
- It did not flag a fact he knew was false and outdated
- When he raised it, the agent folded
Why it’s worth knowing
He knew one fact in the workbook was false because he had put it there himself as a placeholder. The agent still missed it, and only backed down when he pointed it out.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗