this post was submitted on 21 May 2024
133 points (95.2% liked)

Technology

72769 readers
1390 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
 

I often see a lot of people with outdated understanding of modern LLMs.

This is probably the best interpretability research to date, by the leading interpretability research team.

It's worth a read if you want a peek behind the curtain on modern models.

you are viewing a single comment's thread
view the rest of the comments
[–] Womble@lemmy.world 27 points 1 year ago* (last edited 1 year ago) (13 children)

This is a really good science communication article, it describes their work in clear terms (finding structures that relate to abstract concepts, seeing when they are activated and how strengthening and weaking them modifies outputs) and goes into the implications for it. I'm probably going to save this link as a rebuttal for the people who claim LLMs just predict the next word and have no concepts embedded in them.

[–] misk@sopuli.xyz 8 points 1 year ago (11 children)

I doubt that anyone saying that LLM are calculating next word solely based on previous sequence. It's still statistics, regardless of complexity.

[–] Womble@lemmy.world 7 points 1 year ago (1 children)

Youd be surprised at the level of unthinking hatred around them, but even discarding that Ive seen it said often that LLMs have no internal model of what they are talking about as they are just next word generators. This quite clearly contradicts that interpretation.

[–] Spedwell@lemmy.world 4 points 1 year ago* (last edited 1 year ago)

concepts embedded in them

internal model

You used both phrases in this thread, but those are two very different things. It's a stretch to say this research supports the latter.

Yes, LLMs are still next-token generators. That is a descriptive statement about how they operate. They just have embedded knowledge that allows them to generate sometimes meaningful text.

load more comments (9 replies)
load more comments (10 replies)