Which flash model wins?
DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯
Okay, I guess I didn't waste all that money after all
Deepseek V4.1 Flash 304 tok/s code, 135 tok/s prose Zero optimization, will have it max optimized by the morning.
A maze game completed in one go using DeepSeek V4.1 Flash
It took less than half an hour to complete the in-depth search.
Amazing. Just when I started glazing Kimi and Deepseek founders for liking Pink Floyd or w/e as maybe a…
Amazing. Just when I started glazing Kimi and Deepseek founders for liking Pink Floyd or w/e as maybe a sign of true local creative thinking, they end up exposed as trade secret thieves who then undercuts pricing to get a competitive edge. A most expected and reliable pattern…
You have reached the end of the archive
All of deepseek