TechTakes

1480 readers

251 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

[email protected]

194

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

submitted 2 months ago by [email protected] to c/[email protected]

139 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] lunarul 4 points 2 months 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?

[–] [email protected] 4 points 2 months ago

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