Press Space to continue
Curated tech Twitter/X posts on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
Press Space to continue
Press Space to continue
AI is about to get a LOT faster... and almost nobody understands why these guys just figured out how to make AI models run at insane speeds let me explain to you how it works: - normally an AI writes its answer one word at a time, and the big model has to do all the heavy work for every single word - these guys pair it with a small, quick helper that guesses the next few words ahead - the big model checks all those guesses in one go instead of word by word - it keeps the guesses it agrees…
EAGLE-4 is here. From EAGLE-1 to EAGLE-3, we’ve kept making inference faster. EAGLE-4 is our fastest yet. 961.6 tokens/s on @Alibaba_Qwen’s Qwen3.8-27B with TokenSpeed (BF16, 4× @NVIDIA B300, TP4, one request, T=0). Github: https://t.co/GwocZk1UTU https://t.co/GawgFNXKWj