this post was submitted on 18 Apr 2025
323 points (94.2% liked)

Technology

69156 readers
3043 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
you are viewing a single comment's thread
view the rest of the comments
[–] Dran_Arcana@lemmy.world 36 points 4 days ago (2 children)

Anecdotally, I use it a lot and I feel like my responses are better when I'm polite. I have a couple of theories as to why.

  1. More tokens in the context window of your question, and a clear separator between ideas in a conversation make it easier for the inference tokenizer to recognize disparate ideas.

  2. Higher quality datasets contain american boomer/millennial notions of "politeness" and when responses are structured in kind, they're more likely to contain tokens from those higher quality datasets.

I haven't mathematically proven any of this within the llama.cpp tokenizer, but I strongly suspect that I could at least prove a correlation between polite token input and dataset representation output tokens

[–] tdawg@lemmy.world 3 points 4 days ago

Honestly they were better until recently. GPT (at least) has gotten really good at de-escalation and providing (mostly) factual responses when you get irate