注册并分享邀请链接,可获得视频播放与邀请奖励。

Together AI
@togethercompute
Accelerate inference, model shaping, and pre-training on a research-optimized platform.
加入 November 2022
371 正在关注    62.6K 粉丝
Web agent economics are set by inference volume and each step is one inference call. A simple task (extract a field, fill a form, navigate a site) is 10 to 20 calls. A multi-site workflow runs into the hundreds. From @RaiseSummit last month: @abhshkdz, @yutori_ai co-founder/CEO, on how they ship Navigator at 2-5x cheaper and faster than closed models on web tasks: -> ~80% prefix cache hit rate -> Speculative decoding on smaller footprint models -> Post-training Qwen models with SFT and RL They run on Together, where customizable endpoints and auto-scaling let them A/B test new model variants in minutes.
显示更多