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.

Geczy

Moved to a repo at https://github.com/Geczy/coolify-migration

zhangjiazhi

deleting data:
select master_modify_multiple_shards(‘delete from github_events where created_at >=  ''2015-01-01 00:00:00’’’)

join:
citus.large_table_shard_count default value 4 treat as large table  , evaluates several possible join order require minimum data to be transferred across network

broadcast join:
replicate the small table

co-located joins:

danguita

Set up your shiny OS X for development

Gist moved!

This gist was moved to its own repo to allow contributions: https://github.com/danguita/osx-for-developers. Feel free to pull request!

Munter

.falconeer-profile {
    .profile {
        margin-top: 8px;
        width: 92px;
        height: 92px;
        background-repeat: none;
    }

    &#ulrik {
        .profile { background-image: url(/images/falconeers/Ulrik-side.png?sprite=falconeers); }