Skip to content

EP4: 谷歌DeepMind研究员揭秘:Coding模型是怎么炼成的,模型上限在哪

March 26, 2026 · 1 h 45 min

Show notes

谷歌DeepMind研究员揭秘:Coding模型是怎么炼成的,模型上限在哪 一线洞察,深度思考。硅谷核心科技从业者,带你触摸AI变革深处。 --- 📌 本期看点 英伟达GTC大会刚刚落幕,大模型在过去半年经历了一轮又一轮的迭代。本期节目,我们请到了前Google DeepMind资深研究员Warren Chen——一位在coding agent方向深耕多年、现已投身创业的一线技术人,和我们做了一场关于大模型训练范式演化的硬核技术对谈。 从Pre-training到RLHF,从Verifiable Feedback到Mid-Training,从Harness Engineering到Agent Environment——Warren用"看课本、做习题、考试"的类比,把大模型训练的三次范式跃迁讲得通透。如果你想理解为什么Coding Agent突然爆发、为什么Anthropic能持续领先、以及创业者该押注什么方向,这期不容错过。 --- 📖 本期术语速查(听到不熟悉的词?翻这里) Pre-training(预训练):让AI把互联网上海量文字都"看"一遍,相当于通读所有课本 SFT(监督微调):给AI做示范题,手把手告诉它"这道题应该这么答" RLHF(人类反馈强化学习):请人类给AI的两个回答打分,AI学着挑人更喜欢的那个 RLVF(可验证反馈强化学习):不用人打分了,直接对答案。

All episodes of 硅谷洞察局 Silicon Valley Insider

Settings

Display

Language

Decides which stations you see first on the home page.

History

Recently played stations and episodes and your latest searches are only stored in this browser.

Notifications

A short notice when a podcast you follow has a new episode. Turn off single podcasts with the bell on their page.

Account

Save favorites – in the app and on the website.

Keyboard shortcuts

/
Open search
Space
Play or pause
← →
In the player: back 15 s, forward 30 s (episodes) · in a row: next tile
↑ ↓
In a row: target within the tile
Home / End
In a row: first or last tile
Esc
Close window or menu
?
This overview
Now playing

Go to station page

Play next

    Add episodes with “Play next” – they play after the current episode.