this post was submitted on 29 Oct 2025
-45 points (20.0% liked)
Technology
76680 readers
2416 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- 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.
- Check for duplicates before posting, duplicates may be removed
- 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
view the rest of the comments
What do LLMs do beyond predicting the next token?
A few months back it was found that when writing rhyming couplets the model has already selected the second rhyming word when it was predicting the first word of the second line, meaning the model was planning the final rhyme tokens at least one full line ahead and not just predicting that final rhyme when it arrived at that token.
It's probably wise to consider this finding in concert with the streetlight effect.
What do you mean by that? What does it mean to "select" something in the context of a neural net with input nodes and output nodes?
How have you come to that conclusion?
Read it for yourself here.
See the "Planning in Poems" section.
Are you able to explain succinctly what you mean by "selected" so that we can communicate? That page is pretty dense and opaque.