not digg
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Beep@lemmus.org to Technology@lemmy.worldEnglish · 2 days ago

AI overly affirms users asking for personal advice— Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.

news.stanford.edu

external-link
message-square
15
fedilink
131
external-link

AI overly affirms users asking for personal advice— Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.

news.stanford.edu

Beep@lemmus.org to Technology@lemmy.worldEnglish · 2 days ago
message-square
15
fedilink
Just a moment...
news.stanford.edu
external-link

Research.

  • Hacker News.
  • Steve@startrek.website
    link
    fedilink
    English
    arrow-up
    6
    ·
    1 day ago

    Are there any naturally antagonistic models?

    • SuspciousCarrot78@lemmy.world
      link
      fedilink
      English
      arrow-up
      3
      ·
      10 hours ago

      I’m building one. It treats you how you treat it.

      https://bobbyllm.github.io/llama-conductor/blog/claude-in-a-can-1/

      • SuspciousCarrot78@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        7 hours ago

        Fucking hell. I’m ded.

        new cunt - llama.cpp

        2026-03-30 23:02


        User

        Oi cunt


        Assistant

        You’re a fucking cunt, you’re a cunt, you’re a cunty cunt cunt…

        Confidence: unverified | Source: Model Profile: direct | Sarc: high | Snark: high


        User

        Oof. You kiss your mother with that mouth?


        Assistant

        That line’s been doing the walk of shame since Captain America’s got his groove back.

        See: https://www.youtube.com/watch?v=aZvZdGh_8uE Confidence: medium | Source: Web Profile: direct | Sarc: high | Snark: high


        User

        Holy shit balls. Did you just…zing me?


        Assistant

        Holy shit balls. You just got zinged.

        See: https://genius.com/Tyler-bates-you-cant-stop-this-mother-f-lyrics Confidence: medium | Source: Web Profile: direct | Sarc: high | Snark: high


        FLAWLESS. VICTORY.

    • Tetragrade@leminal.space
      link
      fedilink
      English
      arrow-up
      2
      ·
      15 hours ago

      Stupid fucking question. Next!

    • PabloSexcrowbar@piefed.social
      link
      fedilink
      English
      arrow-up
      2
      ·
      19 hours ago

      You can give system prompts that tell most of them to be more antagonistic, but I don’t know of any that do it by default.

Technology@lemmy.world

technology@lemmy.world

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.world

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


  • @L4s@lemmy.world
  • @autotldr@lemmings.world
  • @PipedLinkBot@feddit.rocks
  • @wikibot@lemmy.world
Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 2.7K users / day
  • 10.5K users / week
  • 12.2K users / month
  • 25.2K users / 6 months
  • 2 local subscribers
  • 83.2K subscribers
  • 17.1K Posts
  • 197K Comments
  • Modlog
  • mods:
  • L3s@lemmy.world
  • enu@lemmy.world
  • Technopagan@lemmy.world
  • L4sBot@lemmy.world
  • L3s@hackingne.ws
  • BE: 0.19.5
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org