this post was submitted on 13 Oct 2024
195 points (99.5% liked)

TechTakes

1425 readers
211 users here now

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

founded 1 year ago
MODERATORS
dgerard@awful.systems
195
LLMs can’t reason — they just crib reasoning-like steps from their training data (pivot-to-ai.com)
submitted 1 month ago by dgerard@awful.systems to c/techtakes@awful.systems
124 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] lunarul@lemmy.world 4 points 1 month ago (1 children)

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?

[–] DarkThoughts@fedia.io 4 points 1 month ago

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