glizzop
6.1K posts

glizzop
@dogeglizzy
make a wish kid back-to-back champion

Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI

BREAKING: AI-powered humanoid robot accompanies first lady Melania Trump to a White House summit on empowering children with educational technology.


Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI

The Scoring of ARC-AGI-3 doesn't tell you how many levels the models completed but how efficiently they completed compared to humans actually squared efficiency, whatever that means meaning if a human took 10 steps to solve it and the model 100 steps then the model gets a score of 1% ((10/100)^2) so ARC-AGI-1/2 and ARC-AGI-3 scores are not comparable

I need a GitHub too! Is it like that or nah?


















