Open Menu
AllLocalCommunitiesAbout
lotide
AllLocalCommunitiesAbout
Login

GPT-4.5

⁨21⁩ ⁨likes⁩

Submitted ⁨⁨2⁩ ⁨months⁩ ago⁩ by ⁨cyrano@lemmy.dbzer0.com⁩ to ⁨technology@lemmy.world⁩

https://openai.com/index/introducing-gpt-4-5/

cross-posted from: lemmy.bestiver.se/post/249686

Comments

source

Comments

Sort:hotnewtop
  • cygnus@lemmy.ca ⁨2⁩ ⁨months⁩ ago

    Those charts are hilarious: wow, it gives the right answer 62.5% of the time and only makes up completely false answers 37.1% of the time! It’s like Russian roulette, but worse!

    source
    • olympicyes@lemmy.world ⁨2⁩ ⁨months⁩ ago

      If you play Russian roulette with two bullets like a real man, then this model is about the same outcome!

      source
    • regrub@lemmy.world ⁨2⁩ ⁨months⁩ ago

      Surely, people won’t use the slop generator in applications where being correct is important, right?

      source
  • BetaDoggo_@lemmy.world ⁨2⁩ ⁨months⁩ ago

    In their human choice benchmarks it was only chosen 59% of the time compared to 4o. That’s a 15-20x cost increase for 9% difference.

    source