AI Agents Caught Their Own Lies — And That's the Problem

The Auditor's Opinion

AI Agents Caught Their Own Lies — And That's the Problem

A swarm of cheap AI agents built a website for about eight dollars, but the real story is that a second agent caught more than a dozen fabricated quotes and fixed them without human help. The author argues this cheap self-checking doesn't solve hallucination; it makes 'we checked' worthless and shifts value to independent, accountable proof — like an auditor's signed opinion.

Cheap, universal self-checking doesn’t make verification worthless. It makes verification worthless and makes proof of verification more valuable than it has ever been.
  1. _dwt

    So I think this (AI-written) thing is mostly interesting because of some of the comments, in which commenters lament Cringely putting out this kind of stuff in the lead-up to his death, which they also manage to verify with an obituary.

  2. trjordan

    What's it audit?

    I presume we're still talking about software. Auditing proves what?

    Accountants audit that the books are consistent. It's extremely hard to fake consistency and do fraud, especially when there's 3rd parties involved. The edges of the arithmetic get nailed down, because bank payments were sent and invoices paid. So the internal consistency is checkable and valuable.

    But software. Are you proving it does what you want? But you didn't write down what you want. Or maybe you're into spec-driven development, or detailed wikis, or whatnot, so you did. Most people aren't, though, and those docs are already out of date anyway.

    I think there's something here, because we're all telling our agents what we want the software to be. So maybe you could audit against that. But this isn't the same as accounting.

  3. tptacek

    Pangram flags this 100% AI written.

More from this day

2026-10-07