Thread

1. rafram · 1789996190 · focus · HN ↗

   > Shows the evidence behind every flag, so you can disagree with it

   > Logs every Bluetooth device it hears, glasses or not

   How much AGI is required before LLMs stop putting totally irrelevant technical details into marketing copy?

   1. edot · 1789996336 · focus · HN ↗

      I feel as though it’s inherent in the models, as part of “alignment” or whatever. I’ve noticed whenever having an LLM help with data analysis, especially Claude, it just can’t help itself from putting caveats and guides and documentation inline or in footers.

      1. soco · 1789997344 · focus · HN ↗

         And if you correct it, it will mention "a previous version said..."
   2. Trasmatta · 1789997577 · focus · HN ↗

      I also like:

      > Nothing leaves your phone and there is no account.

      This is good to know, but it's the exact type of thing Claude is obsessed with putting everywhere once you tell it NOT to do something. For example, if I tell it to commit but never push changes to GitHub, it can't help but leave "Changes committed; nothing was pushed." to EVERY SINGLE MESSAGE. The model just can't help but report back about everything it's NOT doing, and it drives me crazy.

      1. phoghed · 1789999306 · focus · HN ↗

         I like those kinds of updates (as long as they are accurate of course)

         What’s annoying is the stuff it decides to put into user facing copy, details that they’d never give a shit about, calling everything real, etc

   3. cristoperb · 1790001286 · focus · HN ↗

      I don't mind if models do that but I don't understand why a human doesn't take 2 minutes to proof and re-word/delete them

Unofficial Hacker News client; not affiliated with Y Combinator.