CaptainEmo craftgear

比較

https://jakearchibald.com/2020/avif-has-landed/
- jpg, webpとの比較。画像の種類ごとに実例と考察がありわかりやすい。

表示

Chrome 85以降
Firefox 77以降
- about:configでフラグを立てる必要あり

編集

One of the headaches I have been bugged by is domain knowledge in SQL queries when it comes to configure code base with Onion Architecture.

If you want to filter data, it is not realistic to use Array.filter to filter the data after retrieving it by SQL, as it consumes memory and is bad for performance.

I have no choice but to write the filter conditions in the WHERE clause of SQL, but I thought it might be a good idea to define the conditions in the WHERE clause as constants in the domain layer.

Example: Extracting customers who have purchased more than 1,000,000 yen in the past year as valued customers

Problem

LLM Samplers Explained

Everytime a large language model makes predictions, all of the thousands of tokens in the vocabulary are assigned some degree of probability, from almost 0%, to almost 100%. There are different ways you can decide to choose from those predictions. This process is known as "sampling", and there are various strategies you can use which I will cover here.

OpenAI Samplers

Temperature

Temperature is a way to control the overall confidence of the model's scores (the logits). What this means is that, if you use a lower value than 1.0, the relative distance between the tokens will become larger (more deterministic), and if you use a larger value than 1.0, the relative distance between the tokens becomes smaller (less deterministic).
1.0 Temperature is the original distribution that the model was trained to optimize for, since the scores remain the same.
Graph demonstration with voiceover: https://files.catbox.moe/6ht56x.mp4

Building Claude Code from Source

Step-by-step guide for building the Claude Code CLI from the alesha-pro/claude-code repository — leaked Anthropic Claude Code source code.

Requirements

Linux (Ubuntu 22.04+) or macOS
4GB RAM, 4 CPU cores, 30GB disk
Bun >= 1.3
Git

	#!/bin/sh
	# 使い方
	# cut.sh 開始時間終了時間元のファイル
	#
	# 例) 1時間32分15秒から、1時間34分5秒まで切り取る
	# cut.sh 1:32:15 1:34:05 input.mp4
	ffmpeg -ss $1 -to $2 -i "$3" -vf fade=d=1.0,reverse,fade=d=1.0,reverse -af afade=d=1.0,areverse,afade=d=1.0,areverse -c:a aac output.mp4

	{#
	Qwen3.5-compatible relaxed chat template
	Purpose:
	- allow multiple system messages
	- treat developer messages like system messages
	- merge all leading/interleaved system/developer messages into one system block
	- avoid "System message must be at the beginning"
	#}

	{%- set ns = namespace(