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

Technology

59534 readers
3223 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago
MODERATORS
L3s@lemmy.world
L3s@fry.gs
L4s@fry.gs
L4s@lemmy.world
enu@lemmy.world
133
Mapping the Mind of a Large Language Model (www.anthropic.com)
submitted 6 months ago by kromem@lemmy.world to c/technology@lemmy.world
21 comments fedilink hide all child comments
 

I often see a lot of people with outdated understanding of modern LLMs.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
[–] tabarnaski@sh.itjust.works 7 points 6 months ago (2 children)

I think the most interesting thing in this article is the fact that some concepts central to semantics (analogy, connotation) or psychology (bias) kind of emerge naturally in multi layered neural networks of sufficient size. Also that it can sound like different personalities (overconfident, secretive, delusional) if you manipulate the weight or the proximity of features. I'd like to see the same kind of study but for midjourney...

[–] magic_lobster_party@kbin.run 1 points 6 months ago

I would imagine a similar result. Like how the word “cartoon” activates one particular feature. And if you identify this feature you can control the level of “cartooniness” by tweaking the particular feature.

[–] GiveMemes@jlai.lu 1 points 6 months ago* (last edited 6 months ago)

That's a chicken and egg situation tho. Is the bias a result of a mind? Or is it the result of being trained on data with common human biases all put together by humans? Are these traits actually measurable or are we just anthropomorphizing a machine like we do everything else?