198

LLMs can’t reason — they just crib reasoning-like steps from their training data(pivot-to-ai.com)

posted
by
Avatar
David Gerard@awful.systemsM
in
Avatar
techtakes@awful.systems
130 comments
hidereport
Sort:
HotTopControversialNewOld
You are viewing a single thread.
View all comments View context
Avatar
lunarul@lemmy.world
4 points

My best guess is it generates several possible replies and then does some sort of token match to determine which one may potentially be the most accurate.

Didn’t the previous models already do this?

permalink
report
parent
reply
Avatar
DarkThoughts@fedia.io
4 points

No idea. I’m not actually using any OpenAI products.

permalink
report
parent
reply

TechTakes

!techtakes@awful.systems

Create post

Big brain tech dude got yet another clueless take over at HackerNews etc? Here’s the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

Community stats

  • 1.5K

    Monthly active users

  • 504

    Posts

  • 11K

    Comments

Community moderators