this post was submitted on 26 May 2025
1022 points (98.9% liked)

memes

15113 readers
4413 users here now

Community rules

1. Be civilNo trolling, bigotry or other insulting / annoying behaviour

2. No politicsThis is non-politics community. For political memes please go to !politicalmemes@lemmy.world

3. No recent repostsCheck for reposts when posting a meme, you can only repost after 1 month

4. No botsNo bots without the express approval of the mods or the admins

5. No Spam/AdsNo advertisements or spam. This is an instance rule and the only way to live.

A collection of some classic Lemmy memes for your enjoyment

Sister communities

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] brucethemoose@lemmy.world 36 points 1 week ago* (last edited 1 week ago) (1 children)

There’s some technical reasons this is 100% accurate:

  • Some tokenizers are really bad with numbers (especially some of OpenAI’s). It leads to all sorts of random segmenting of numbers.

  • 99% of LLMs people see are autoregressive, meaning they have once chance to pick the right number token and no going back once it’s written.

  • Many models are not trained with math in mind, though some specialized experimental ones can be better.

  • 99% of interfaces people interact with use a fairly high temperature, which literally randomizes the output. This is especially bad for math because, frequently, there is no good “synonym” answer if the correct number isn’t randomly picked. This is necessary for some kinds of responses, but also incredibly stupid and user hostile when those knobs are hidden.

There are ways to improve this dramatically. For instance, tool use (eg train it to ask Mathematica programmatically), or different architectures (like diffusion LLMs, which has more of a chance to self correct). Unfortunately, corporate/AI Bro apps are really shitty, so we don’t get much of that…

[–] vivendi@programming.dev 4 points 1 week ago

Exactly, a lot of the "AI Panic" is from people using ClosedAI's dogshit system, non-finetuned model and Instruct format.