this post was submitted on 15 Oct 2024
492 points (96.4% liked)

Technology

59651 readers
2617 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
L4s@lemmy.world
L3s@fry.gs
L4s@fry.gs
enu@lemmy.world
492
Apple study exposes deep cracks in LLMs’ “reasoning” capabilities (arstechnica.com)
submitted 1 month ago by misk@sopuli.xyz to c/technology@lemmy.world
109 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] zbyte64@awful.systems 3 points 1 month ago

Adding the benchmark back into the training process doesn't mean you get an LLM the can weed out irrelevant data, what you get is an LLM that can pass the new metric and you have to design a new metric with different semantic patterns to actually know if it's "eliminating red herrings".