‹ BackHN Continuity

Thread

AI chatbots give wrong answers to financial queries 'most of the time'

157 points · 89 comments · 1vuio0pswjnm7

  1. ehe78qhe · · focus · HN ↗
    Article is just a vague summary of <a href="https:&#x2F;&#x2F;www.saturnos.com&#x2F;report&#x2F;artificial-authority">https:&#x2F;&#x2F;www.saturnos.com&#x2F;report&#x2F;artificial-authority

    Anecdotally, current models seem to be decent at general personal finance principles - certainly better than the majority of personal finance education that people get exposed to unless they seek it out and read a variety of books and sources. But I wouldn&#x27;t trust them with direct decision making with actual money due to the training lag time on current tax policy, etc.

    1. NitpickLawyer · · focus · HN ↗
      &gt; certainly better than the majority of personal finance education that people get exposed to unless they seek it out and read a variety of books and sources.

      Also, models are now good enough that you can give them chapters from &quot;authoritative&quot; books, and they&#x27;ll integrate that and come up with better answers even if their &quot;vanilla&quot; answers were average. And they&#x27;ll tailor stuff to your particular situation. It&#x27;s funny that the &quot;agentic&quot; stuff is only used in coding mostly, while it can and does work in other fields as well.

      As always, you kinda need to check it (at least spot check) but all in all I&#x27;d agree it&#x27;s better than the average stuff you used to find with a quick google search.

      1. legostormtroopr · · focus · HN ↗
        So if you know a book that has the information you need, you just need to upload it into the model to get the right answer.

        Isn&#x27;t that a bit circular - if you already know the authoritative source, why ask a model?

        1. lconnell962 · · focus · HN ↗
          Some of the more widely spread and tolerated LLM outputs seem to be AI slop replacing Journalism&#x2F;Blog slop. Places where people complained about quality already, but tolerated it if important enough.

          So to name some of the more common ones Translation, Summarization, and Reiteration of a source material.

          Humans put spin on things, how much you trust a source might not reflect the source&#x27;s factual accuracy. It might just mean you liked reading it better from one source than another.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.