You can use strace on a specific pid to figure out what a specific process is doing, e.g.:
strace -fp <pid>
You might see something like:
select(9, [3 5 8], [], [], {0, 999999}) = 0 (Timeout)
| // Use Gists to store code you would like to remember later on | |
| console.log(window); // log the "window" object to the console |
| #!/bin/bash | |
| ## | |
| # Обновление тестовых версий (EAP) сред разработки компании JetBrains для Linux. | |
| # В данном случае скачивается PhpStorm, но скрипт подойдёт для любой среды разработки, | |
| # выкладываемой компанией JetBrains в EAP. | |
| # | |
| # | |
| # @author MaximAL | |
| # @since 2015-08-27 Поменял паттерн `fileRegex` под текущие реалии. | |
| # @since 2015-04-10 Первая версия |
| #!/bin/bash | |
| # Build a commit frequency list. | |
| ROW_LIMIT=20 | |
| git log --name-status $* | \ | |
| grep -E '^[A-Z]\s+' | \ | |
| cut -c3-500 | \ | |
| sort | \ | |
| uniq -c | \ |
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.