Zain
@zainhas
I build and teach AI • AI/ML @togethercompute • EngSci ℕΨ/PhD @UofT • Previously: vector DBs, data scientist, lecturer & health tech founder • 🇺🇸🇨🇦🇵🇰
加入 August 2012
2.1K 正在關注 8.3K 粉絲
deepseek-v4.1 flash -- for once a model where the reasoning_effort scales the output quality and token output nice and ~linearly
> quality improves nicely with reasoning effort setting 1 to 100
> Avg output tokens also scale nicely with effort
顯示更多
