AI エージェントとは何か — チャットボットと何が違うのか
AI エージェントとは、呼び出せるツールと追うべき目標を与えられ、各ステップで人間に尋ねずに複数の手順を進める権限を持った言語モデルである。チャットボットは質問に答えて止まるが、エージェントは目標が達成されたと判断するか、予算を使い切るまで行動し続ける。
更新 約5分
解説
繰り返し出てくる AI の疑問に、平易な言葉で答えます。分野の変化に合わせて更新します。
What is a context window, and why does it run out?
A context window is the maximum amount of text, measured in tokens, that a model can consider in a single request. It holds the system instructions, the conversation so far, any documents you paste in, and the answer being generated. When the total exceeds the limit, something has to be dropped or summarised.
更新 約4分
RAG（検索拡張生成）とは何か、いつ必要か
検索拡張生成とは、質問に関連する箇所を自社の文書から探し出し、それをモデルのプロンプトに入れて、その内容にもとづいて答えさせる方式である。モデルの重みは変わらない。知識はリクエスト時にコンテキストとして届く。
更新 約4分
Open weights vs open source AI: what the labels actually mean
Open weights means the trained model file can be downloaded and run yourself, under whatever licence the publisher chose. Open source is a stricter legal standard requiring freedom to use, study, modify and redistribute without restrictions on field of use. Many widely used models are open weights but not open source.
更新 約3分
Why does AI use so much electricity?
AI accelerators draw far more power per rack than traditional servers, and that power has to be delivered, cooled and paid for continuously. Training a large model is a one-off spike; serving it to millions of users is a permanent load, and inference is what dominates energy use over a deployed model's life.
更新 約4分
How AI model pricing actually works: tokens, caching and batching
Almost every AI API bills per million tokens, with separate prices for input and output. Output usually costs several times more than input. Cached input, batch processing and smaller models can each cut the bill substantially, and the total for a conversation grows with history because most APIs re-send the whole thread every turn.
更新 約3分