Long term, we think the right way to orchestrate open source and frontier models is to post-train them to get good at advisor escalation to a frontier expensive model when necessary, inside an agent harness that’s already deployed in production to millions of users. Perplexity is…
— Aravind Srinivas (@AravSrinivas) July 9, 2026
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。