Hippocampus's Garden

Some LLMs disable sampling knobs like temperature and top_p. Here’s why.

A deep dive into how LLMs serialize prompts, output schemas, and tool descriptions into a token sequence, with examples from Llama 4's implementation.

『アンネの日記』をGPT-4.1で日本語に翻訳しました。

『コンピュータの構成と設計』（通称「パタヘネ本」）のまとめと感想です。

A deep dive into how databases work.

Learn how to extend Claude's capabilities by building your own Model Context Protocol server.

成長意欲の高い人が自己肯定感を保つのに役立つ実践的なツールを紹介します。

A detailed guide on how to build applications with foundation models.

2024年に読んだ本を振り返ります。

Ordinal regression has order structure between classes and there are dedicated loss functions to use this information.