@JundeMorsenWu Bro your company has been accused of distilling other models like Google Gemini, Anthropic etc . Sitting here pretending to be a genius is actually quite funny . Once they close all those loopholes you use, you’ll magically stop ‘ inventing ‘ too.
> been paying $200/month for cloud AI APIs
> laptop: M2 MacBook, 16GB RAM
> tried running models locally, garbage quality after 4K tokens
> read this TurboQuant breakdown on Tuesday
> applied 3-bit KV cache compression
> same MacBook now runs 100K token conversations
> quality: identical to cloud
> cancelled all API subscriptions Wednesday
> it's been 3 days
> saved $200/month forever
> with a free algorithm from a free paper
> my MacBook didn't change. the math did