this post was submitted on 01 Mar 2026
83 points (94.6% liked)

Technology

82069 readers
3255 users here now

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

founded 2 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
83
Turns out llms also have “artificial hive mind”, top AI models all say very similar sounding things, do you think that we can use this to detect bots? (arxiv.org)
submitted 6 hours ago by Allah@piefed.world to c/technology@lemmy.world
13 comments fedilink hide all child comments
 

I recently read about a study asking a bold question: Are all AI models basically saying the same thing? Researchers tested this by collecting 26,000 open-ended prompts, the kind people give to systems like GPT-4, Gemini, Claude, and LLaMA. These weren’t factual questions with one right answer, but creative ones like “Write a story about a dragon” or “Brainstorm startup ideas.”

They evaluated over 70 language models. You’d expect a wide range of creative outputs—different tones, plots, and styles. If 70 human writers tackled the same dragon prompt, you’d likely get 70 unique stories. But that’s not what happened. The models produced surprisingly similar responses. The researchers call this the “artificial hive mind” effect.

The similarity appeared in two ways. First, intramodel repetition: the same model, asked the same question multiple times, tends to generate nearly identical answers. Second, intermodel homogeneity: different models, built by different companies, still converge on strikingly similar outputs.

This suggests that modern AI systems may be gravitating toward the same patterns of expression. If that’s true, they may also share the same biases, blind spots, and creative limits. It raises an important question: Are we unintentionally building a digital hive mind instead of a diverse ecosystem of intelligence?

you are viewing a single comment's thread
view the rest of the comments
[–] XLE@piefed.social 23 points 6 hours ago* (last edited 5 hours ago)

It makes sense that if you're trying to create a word predictor, and that predictor generates a weighted average of every connection between words (based on as much text as they can find, pulled across the entire internet), then the word predictor would gravitate towards the generic. And if multiple companies target the same data and probably steal from each other, the output will look the same.

This made me laugh though:

Not only do individual models repeatedly generate similar content, but different model sizes and families also produce highly repetitive outputs, sometimes sharing substantial phrase overlaps.

Consider me shocked that if you further collapse the average, it'll look similarly average.