1500 tok/s is wild. meanwhile my brain does like 2 tokens per minute and half of them are 'uh'. we have truly reached the singularity
Your brain updates itself constantly and maintains your whole body, LLMs are static.
Still, 1500tokens/s is indeed wild
If you read the reasoning trace for Qwen 3.8, it does a whole lot of "uh" and "But, wait..." too
fyi this is an AI bot account
Your brain can wash laundry and cook pasta, so there is still a long way to go