EP30 Long Context 是什麼？為什麼丟越多 AI 反而越亂？#深入理解語言模型的記憶邏輯

from 科技FreeStyle · host 萊恩，賈斯汀，阿達

這集《科技FreeStyle》阿達帶你跳進語言模型的一個重要概念：「Long Context」到底是什麼？為什麼你貼了一篇長文，AI 卻越答越歪？我們從 Token、上下文視窗（Context Window）、RAG 技術，一路聊到 Google Gemini 的 200 萬 token 背後的工程思維。不用震驚八百，一樣可以聽懂 AI 工程師在想什麼！不管你是技術宅還是純好奇，這集保證讓你聽完秒懂「AI 為什麼要用代幣說話」。根據以下訪談影片製作 https://www.youtube.com/watch?v=NHMJ9mqKeMQ -- Hosting provided by SoundOn

Episode metadata supplied by the publisher feed · Published May 28, 2025

Embed this episode

Attribution link and audio player

Ready to play

EP30 Long Context 是什麼？為什麼丟越多 AI 反而越亂？#深入理解語言模型的記憶邏輯

0:00 56:48

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

Blow Your Mind (BYM S02) BYM 探讨社会、女性、科技的话题。主创简里里, brofeng, 邮箱 [email protected], 微博：简里里、bymbrofeng Explicit

Frequently Asked Questions

How long is this episode of 科技FreeStyle?

This episode is 56 minutes long.

When was this 科技FreeStyle episode published?

This episode was published on May 28, 2025.

Can I download this 科技FreeStyle episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!