A practical working guide for coding with LLM agents
Inspired by Andrej Karpathy’s workflow principles
Discover gists
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <title></title> | |
| <meta charset="utf-8" /> | |
| <script src="Scripts/jquery-1.9.1.min.js"></script> | |
| <link href="Content/bootstrap.min.css" rel="stylesheet" /> | |
| <script src="Scripts/isRockFx.js"></script> | |
| <script> | |
| $(function () { |
| Полезные ключи программы psql | |
| -U - Указываем пользователя, например postgres | |
| -W - Приглашение на ввод пароля | |
| -d название_БД - Подключение к БД название_БД | |
| -h имя_хоста - Подключение к хосту имя_хоста | |
| -p порт - По какому порту постгря ожидает подключения | |
| -c команда - Выполнение команды SQL без выхода в интерактивный режим | |
| -f file.sql - Выполнение команд из файла file.sql | |
| -S - Однострочный режим, то есть, переход на новую строку будет выполнять запрос (избавляет от ; в конце конструкции SQL) |
| #EXTM3U | |
| #EXTINF:-1 tvg-id="" tvg-name="A Fazenda Nova Chance HD" tvg-logo="https://i.imgur.com/FuRKLSq.png" group-title="Premiere",A Fazenda Nova Chance HD | |
| http://giantofthefuture.gleeze.com:25461/live/colepty1679/Hbplloxye/4776.ts | |
| #EXTINF:-1 tvg-id="" tvg-name="A Fazenda Nova Chance (Apenas Brasil)" tvg-logo="https://i.imgur.com/FuRKLSq.png" group-title="Premiere",A Fazenda Nova Chance (Apenas Brasil) | |
| https://afazendaoitohls1-lh.akamaihd.net/i/afazendaoitohls1_1@379189/index_480_av-p.m3u8 | |
| #EXTINF:-1 tvg-id="" tvg-name="A Fazenda Nova Chance HD Alternativo (Apenas Brasil)" tvg-logo="https://i.imgur.com/FuRKLSq.png" group-title="Premiere",A Fazenda Nova Chance HD Alternativo (Apenas Brasil) | |
| https://afazendaoitohls1-lh.akamaihd.net/i/afazendaoitohls1_1@379189/index_720_av-p.m3u8 | |
| #EXTINF:-1 tvg-id="" tvg-name="A Fazenda Nova Chance Alternativo (Apenas Brasil)" tvg-logo="https://i.imgur.com/FuRKLSq.png" group-title="Premiere",A Fazenda Nova Chance Alternativo (Apenas Brasil) | |
| https://afazendaoitohls1-lh.akamaihd.n |
| #!/usr/bin/env bash | |
| set -euo pipefail | |
| # ───────────────────────────────────────────────────────────────────────────── | |
| # uat provisioner — LXQt + Chrome acceptance-testing desktop under qemu:///system. | |
| # Runs entirely as your normal user (no sudo): disks live in a path you own, | |
| # and libvirtd (already root) does the privileged VM/network work. | |
| # Keep uat-cloud-init.yaml and uat-net.xml next to this script. | |
| # ───────────────────────────────────────────────────────────────────────────── | |
| # Pin a clean PATH so a custom python (pyenv/conda/etc.) can't shadow the system |
Fix for Claude Code (and any large HTTPS upload) failing with
API Error: Unable to connect to API (ECONNRESET) on a specific home network.
- Short Claude requests always work; long sessions reset after ~5–13 min.
- Works fine on a phone hotspot, fails on home Wi-Fi.
- Debug log shows the same request retried 11 times, each dying at a
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.
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.
| name | cognitive-rhythm-writing |
|---|---|
| description | 説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替(観察→逡巡→断定→再観察)と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。 |
密度の高い文章が退屈になるのは、情報が多いからではなく、全文が同じ認知モードで書かれているからである。 この規範は、読者の認知モード(観察する、迷う、確信する、確かめ直す)を意図的に切り替え、常に「続きを読む理由」を維持することで、読み進める推進力を作る。
| { | |
| "1969 Toyota 2000 GT": "247", | |
| "1964 Ferrari 250 GTO": "249", | |
| "1954 Mercedes-Benz 300 SL": "251", | |
| "1994 Ferrari F355 Berlinetta": "253", | |
| "1991 Ferrari 512 TR": "255", | |
| "1973 Porsche 911 Carrera RS": "260", | |
| "1995 Porsche 911 GT2": "261", | |
| "2004 Porsche 911 GT3": "262", | |
| "1982 Porsche 911 Turbo": "265", |