筛选结果
8 篇排序
20:55EN → 简体中文
AI Engineer· 2026年10月26日Jesse Hall：语音智能体要为对话而优化，而非只看排行榜Jesse Hall · LiveKitLiveKit 的 Jesse Hall 解释了为什么语音智能体必须像实时系统一样接受评测：听清用户、允许打断、在工具调用期间继续对话，并在用户真正听到声音之前控制延迟。
18:27EN → 简体中文AI Engineer· 2026年10月26日Daksh Gupta：如何打造更好的 AI 代码审查智能体Daksh Gupta · GreptileGreptile 联合创始人 Daksh Gupta 解释了为什么仅靠 webhook 和编程智能体，无法做好 PR 审查；他还介绍了如何通过定向提示词、事故数据、模型反转、代码库上下文、浏览器测试和按任务路由模型来改进审查质量。
17:42EN → 简体中文AI Engineer· 2026年10月21日更快的模型，真的更快吗？要看任务做完没有，而不是 token 有多快Morgan Suo · MiniMaxMiniMax 的 Morgan Suo 逐一拆解 M3.1 Flash 内部的工程改动，追问用户真正关心的问题：分析师要的那份活，是不是真的做得更快、更便宜、也更对了？
22:32EN
No Priors: AI, Machine Learning, Tech, & Startups· 2025年2月7日播客 · 2 人对谈The $5.5 Million Was Only the Last Mile主持 Sarah Guo, Elad GilOn No Priors' 100th episode, Sarah Guo and Elad Gil separate DeepSeek's paper cost from the compute behind it, then walk through OpenAI's Deep Research, Stargate, and their bets for 2025.
23:37ENNo Priors: AI, Machine Learning, Tech, & Startups· 2025年1月9日播客 · 2 人对谈A Hundred GPUs in Seconds: Why Modal Threw Out Docker and Kubernetes主持 Sarah Guo, Elad GilErik Bernhardsson tells Elad Gil that AI inference is too bursty for year-long GPU contracts, and that the cloud should feel as fast as a laptop.
29:09ENNo Priors: AI, Machine Learning, Tech, & Startups· 2024年5月9日播客 · 2 人对谈The Hyperscalers Are Spending $200 Billion — and the Next Bottleneck Is a Power Plant主持 Sarah Guo, Elad GilSarah Guo and Elad Gil walk through music models, on-device LLMs, long context, and why AI capex now sits beside oil and broadband.
26:03ENNo Priors: AI, Machine Learning, Tech, & Startups· 2024年4月11日播客 · 2 人对谈GPT-4-Class Models Will Be Cheap. The Frontier Will Still Need a Patron.主持 Sarah Guo, Elad GilSarah Guo and Elad Gil walk through Mosaic’s Law, Microsoft’s Inflection hire, where the real money sits, and why the first AI wave looks consumer.
23:57ENNo Priors: AI, Machine Learning, Tech, & Startups播客 · 2 人对谈Chips, Agents and a Reckoning: Sarah Guo and Elad Gil on the 2023 AI Boom主持 Sarah Guo, Elad GilThe hosts answer listener questions on the GPU crunch, how soon enterprises will ship AI products, how to build agents, and what 2024 holds for tech valuations.