正在加载视频...
视频加载失败
This is wild! Llama 3.1 405B Instruct finally solves a famous math puzzle that was originally posted on /LocalLlama. To the best of my knowledge, every model (including Claude 3.5 Sonnet and GPT-4o) fails at this task. A longer video coming soon!
11 条评论

elvis1 年前
Full video with an overview and test cases of the Llama 3.1 release:

RedDeer.Games4 年前
Bring Your Switch To Life With The "Triple-A Clock" #AAAClock ⬅️ ➡️ #OLED Ready #NintendoSwitch

Juggalos For Context🌴🥥1 年前
Was the answer in the training data?

elvis1 年前
Could be! I need to try different variants as I mentioned in the video.

明1 年前
@aidan_mclau

Lior⚡1 年前
Huge!

Jasper1 年前
We supported Llama 3.1 405B model on our distributed GPU network at @hyperbolic_labs. Come and use the API for FREE at

Shadow1 年前
It is wild, man 🔥

Sivaram Raju1 年前
That's incredible! 🎉

Skandarux.py1 年前
Maybe it was included in training data ?

Andres Gomez Sarmiento1 年前
Interesting test, but Claude Sonnet got it right for me:
