Picked up a hitch-hiker. Seemed like a nice guy.
After a few miles, he asked me if I wasn't afraid that he might be a serial killer?
I told him that the odds of two serial killers being in the same car were extremely unlikely
@MEXC I am writing to report an issue with my Qubic (QUBIC) transfer.
It has been "Pending" (or "Processing") for a long time and has not been reflected in my account yet.
• Currency: Qubic (QUBIC)
• Transaction ID (TXID): pefatauayrgeraxfopytzdkudzbdljkciiwkcaiswgoiszoelmcymihfzzjn
NVIDIA just trained a 14-billion-parameter AI using evolution, not calculus.
Every AI today learns through backpropagation.
It computes gradients, adjusts weights, repeats.
It works, but it demands precision hardware and enormous GPU clusters.
Evolution Strategies offered an alternative.
Mutate the model, test it, keep what works. Like biological evolution.
The problem was speed. Random mutations on GPUs were painfully slow.
EGGROLL fixes this with one trick.
It splits huge random matrices into two small ones per mutation.
The model mutates, tests, and keeps what works.
Hundreds of thousands of mutations run at once.
> 100x faster training throughput
> 91% speed of pure inference
> Pretrains models using only integers
> Competitive with backprop on reasoning
> Works on non-differentiable systems
It pretrained a language model from scratch using zero gradients.
It also matched reinforcement learning methods on math reasoning tasks.
Everyone kept scaling the calculus to train massive AIs.
It turns out, we just needed to evolve.