yanhua1010

工作流与子代理的模型智能分配

模型能力画像

排名数字越高越好。Cost 反映实际支付成本而非标价(OpenAI 额度非常宽松);Intelligence 指可以无监督托付的问题难度;Taste 涵盖 UI/UX、代码质量、API 设计和文案。

model	cost	intelligence	taste
gpt-5.5	9	8	5
sonnet-5	5	5	7

karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

unixzii

// ==UserScript==
// @name         Fuck X
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  Save your eyes while using X (formerly Twitter)
// @author       Cyandev <unixzii@gmail.com>
// @match        https://twitter.com/*
// @grant        none
// ==/UserScript==

chenyukang

use wget to download website

wget --reject-regex "(.*)\?(.*)" --mirror --no-parent --convert-links -p -U Mozilla https://program-think.blogspot.com/

replace abs path to relative path

find . -type f -name '*.html' -exec sed -i '' 's|https://program-think.blogspot.com/|/|g' {} +

wych42

module demo/mysqlperf

go 1.20

require github.com/go-sql-driver/mysql v1.7.1

joshbuchea

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

Example