Skip to content

KbWen

介面語言 · Interface

Start Here
Search
Categories
Lab
About

Home » Tags

NLP

Editor's picks

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何不直接處理完整字詞：解析字級、字元級、子詞級三種 tokenization 方法，包含 BPE 示範程式碼，以及 token 數量對計費和上下文長度的影響。

NLP

See all 8

AI Systems Read in English

Embedding 是什麼？AI 怎麼知道兩句話意思一樣

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

AI Systems 看中文版

How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

Why Does AI Forget What You Said Earlier?

AI Systems 看中文版

Why Does AI Forget What You Said Earlier?

Chat with an AI long enough and it ignores the rules you set up top; open a new chat and it's blank. It isn't 'forgetting' — it has no memory. Every reply, it re-reads the whole conversation from scratch. Here's what the context window is, and how it differs from ChatGPT's 'memory' feature.

為什麼 AI 會忘記我前面說過的話？

AI Systems Read in English

為什麼 AI 會忘記我前面說過的話？

跟 AI 聊久了，它就忘記你開頭交代的事；開新對話更是整個忘光。背後的原因是它根本沒有記憶——每次回你都是把整段對話重讀一遍。用一個失憶但讀很快的人的畫面，聊聊 context window 是什麼，還有它跟 ChatGPT 那個「記憶」功能差在哪。

AI 連草莓有幾個 r 都數錯，是它笨嗎？

AI 連草莓有幾個 r 都數錯，是它笨嗎？

叫 AI 數 strawberry 有幾個 r，它曾經很有自信地答錯。新模型現在大多答對了，但它當初為什麼會錯——用一個積木的比喻聊聊，順便講為什麼那個原因到現在還沒真的消失。

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何不直接處理完整字詞：解析字級、字元級、子詞級三種 tokenization 方法，包含 BPE 示範程式碼，以及 token 數量對計費和上下文長度的影響。

LLM

AI Systems Read in English

Embedding 是什麼？AI 怎麼知道兩句話意思一樣

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

AI Systems 看中文版

How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

Why Does AI Forget What You Said Earlier?

AI Systems 看中文版

Why Does AI Forget What You Said Earlier?

Chat with an AI long enough and it ignores the rules you set up top; open a new chat and it's blank. It isn't 'forgetting' — it has no memory. Every reply, it re-reads the whole conversation from scratch. Here's what the context window is, and how it differs from ChatGPT's 'memory' feature.

為什麼 AI 會忘記我前面說過的話？

AI Systems Read in English

為什麼 AI 會忘記我前面說過的話？

跟 AI 聊久了，它就忘記你開頭交代的事；開新對話更是整個忘光。背後的原因是它根本沒有記憶——每次回你都是把整段對話重讀一遍。用一個失憶但讀很快的人的畫面，聊聊 context window 是什麼，還有它跟 ChatGPT 那個「記憶」功能差在哪。

AI 連草莓有幾個 r 都數錯，是它笨嗎？

AI 連草莓有幾個 r 都數錯，是它笨嗎？

叫 AI 數 strawberry 有幾個 r，它曾經很有自信地答錯。新模型現在大多答對了，但它當初為什麼會錯——用一個積木的比喻聊聊，順便講為什麼那個原因到現在還沒真的消失。

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何只讀 Token？

Token 是什麼？LLM 為何不直接處理完整字詞：解析字級、字元級、子詞級三種 tokenization 方法，包含 BPE 示範程式碼，以及 token 數量對計費和上下文長度的影響。

word2vec

AI Systems Read in English

Embedding 是什麼？AI 怎麼知道兩句話意思一樣

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

AI Systems 看中文版

How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

TensorFlow 練習 4：word2vec

Machine Learning

TensorFlow 練習 4：word2vec

TensorFlow 練習：用 skip-gram 實作 word2vec 詞向量，並拆開 nce_loss 那一行：訓練時為什麼不掃整張詞彙表，改抽 K 個負面樣本問是非題，以及那些負面樣本是怎麼抽出來的。

Context Window

Why Does AI Forget What You Said Earlier?

AI Systems 看中文版

Why Does AI Forget What You Said Earlier?

Chat with an AI long enough and it ignores the rules you set up top; open a new chat and it's blank. It isn't 'forgetting' — it has no memory. Every reply, it re-reads the whole conversation from scratch. Here's what the context window is, and how it differs from ChatGPT's 'memory' feature.

為什麼 AI 會忘記我前面說過的話？

AI Systems Read in English

為什麼 AI 會忘記我前面說過的話？

跟 AI 聊久了，它就忘記你開頭交代的事；開新對話更是整個忘光。背後的原因是它根本沒有記憶——每次回你都是把整段對話重讀一遍。用一個失憶但讀很快的人的畫面，聊聊 context window 是什麼，還有它跟 ChatGPT 那個「記憶」功能差在哪。

Embeddings

AI Systems Read in English

Embedding 是什麼？AI 怎麼知道兩句話意思一樣

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

AI Systems 看中文版

How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

RAG

AI Systems Read in English

Embedding 是什麼？AI 怎麼知道兩句話意思一樣

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

AI Systems 看中文版

How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

All posts (8)

Embedding 是什麼？AI 怎麼知道兩句話意思一樣
How Embeddings Work: How AI Knows Two Sentences Mean the Same Thing
Why Does AI Forget What You Said Earlier?
為什麼 AI 會忘記我前面說過的話？
AI 連草莓有幾個 r 都數錯，是它笨嗎？
Token 是什麼？LLM 為何只讀 Token？
Google NLP API parsing
TensorFlow 練習 4：word2vec

© 2026 KbWen Blog · Tags · Archive · Contact · Privacy Policy · Powered by Hugo & PaperMod

Support My Work

Buy Me a Coffee