38

"Notably, O3-MINI, despite being one of the best reasoning models, frequently skipped essential proof steps by labeling them as "trivial", even when their validity was crucial."

you are viewing a single comment's thread
view the rest of the comments
[-] bitofhope@awful.systems 22 points 1 week ago

Essentially they do not simply predict the next token

looks inside

it's predicting the next token

[-] froztbyte@awful.systems 15 points 1 week ago

every time I read these posters it's in that type of the Everyman characters in the discworld that say some utter lunatic shit and follow it up with "it's just [logical/natural/obvious/...]"

[-] o7___o7@awful.systems 9 points 1 week ago

Stands to reason

[-] pennomi@lemmy.world 1 points 1 week ago

Read the paper, it’s not simply predicting the next token. For instance, when writing a rhyming couplet, it first plans ahead on what the rhyme is, and then fills in the rest of the sentence.

The researchers were surprised by this too, they expected it to be the other way around.

[-] bitofhope@awful.systems 18 points 1 week ago

Oh, sorry, I got so absorbed into reading the riveting material about features predicting state name tokens to predict state capital tokens I missed that we were quibbling over the word "next". Alright they can predict tokens out of order, too. Very impressive I guess.

[-] froztbyte@awful.systems 15 points 1 week ago* (last edited 1 week ago)

first plans ahead

predict

to declare or tell in advance; prophesy; foretell;

ahead

Strongest matches: advanced; along; before; earlier; forward

stop prompting LLMs and go read some books, it'll do you a world of good

this post was submitted on 07 Apr 2025
38 points (100.0% liked)

TechTakes

1788 readers
82 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 2 years ago
MODERATORS