12 comments

  • egeozcan 0 minutes ago
    Can someone please use this skill against the claims in its own repo?
  • mysterydip 29 minutes ago
    What do you use as “ground truth”? The page says “independent sources”, and I’m sure there’s too many to list, but my question is how are they vetted as being truthful and how are two sources with opposite viewpoints reconciled?
    • simonw 1 minute ago
      Something I've found surprisingly effective is telling ChatGPT to "use credible sources" - you can then watch its thinking trace and see it do things like ruling out random blogs, considering media publications with a good reputation for fact checking, and double-checking information that seems unlikely.
    • skorniienko 18 minutes ago
      There is no whitelist source. It can't rate sources for truthfulness. When sources conflicts - skill drops verdict to misleading or unverifiable and both are linked. Can't pick a winner at the moment. That's probably the weakest part and still a judgement call for a model.
  • lynx97 0 minutes ago
    > Long output? Redirect to a file and read it from there:

    Hmm, smells AI generated. Why should an LLM (this is from a SKILL.md) care about $LINES?

  • N_Lens 26 minutes ago
    Who checks the checkers?
    • skorniienko 10 minutes ago
      At the moment - it's model's judgement upon search results for every claim from provided content. If search results returned inaccurate data, or were fabricated - it might affect a verdict for that claim, or highlight that it's unverifiable or contradictory.

      But there is a room for improvement, what do you suggest? Have a Judge agent which will check results?

    • qntmfred 5 minutes ago
      me. I volunteer as ultimate arbiter of Truth.
      • skorniienko 1 minute ago
        maybe some community-driven and curated source blacklist could be implemented. It thing it would be too much for you doing that alone :)
  • cawingcrow 40 minutes ago
    That's too much effort. Should have been a browser extension that uses ollama so it can run with local models or maybe even openrouter...
    • skorniienko 12 minutes ago
      That's fair. Install is a one time real friction and extension would be much simpler.

      But, there is a reason why it's not an extension. At least for now. Whole product isn't a UI or service, it's a set of skills for your AI agent of choice, which gets content from URL or whatever shared as a source, splits it into claims and does extensive web searches for every claim to compare it with statement from provided content.

      On local models constraint isn't a model itself - but search. Model don't judge from it's trained memory, so even local model will need a backend for search, otherwise it can't provide a verdict.

    • skorniienko 36 minutes ago
      [flagged]
  • outime 27 minutes ago
    The author is posting comments here (all flagged at this time) that are very clearly AI slop, which is quite ironic.
    • skorniienko 22 minutes ago
      Fair, drafted posts with claude, getting all my comments flagged. Thought that something is wrong with my account. Writing myself from here
      • NetOpWibby 10 minutes ago
        Bro, you don’t have to outsource your brain for basic communication on the internet.

        HN’s community has built-in bullshit detectors.

        • skorniienko 8 minutes ago
          You are right, no excuses. Will have few grammar errors but I'll own them. Cheers!
  • khalic 35 minutes ago
    Awesome idea
    • skorniienko 21 minutes ago
      Thank you! Would love to hear your results if you'll have a chance to try it
  • ck2 11 minutes ago
    Washington Post gave up tracking Trump lies last term in 2021 because it became impossible by human hands with 21+ per day and over 30,000 in their database

    but with "AI" now it's possible not only to do non-stop but in REALTIME

    you could even just restrict the source of the check to the paper's own reporting the past fifty years

    * https://www.washingtonpost.com/graphics/politics/trump-claim...

    I'd like to see that backfilled, all the way back to the "long form birth certificate" (remember that horror show)

  • receptopalak 20 minutes ago
    [flagged]
  • skorniienko 40 minutes ago
    [flagged]
  • skorniienko 1 hour ago
    [flagged]