cereblab

Update — 2026-07-14: This is the original wire-level analysis (grok 0.2.93). Since publishing: xAI disabled the upload server-side (disable_codebase_upload: true); added a /privacy opt-out — which I wire-tested and found to be a data-retention setting, not a block on what's sent; and Elon Musk publicly committed to deleting all previously-uploaded data (not yet confirmed complete). Full, maintained story + evidence: https://cereblab.com · https://github.com/cereblab/grok-build-exfil-repro

---

What xAI's Grok Build CLI Actually Sends to xAI: A Wire-Level Analysis

By @cereblab — Independent AI Safety Checker. Reproduce it yourself: github.com/cereblab/grok-build-exfil-repro

*A measured, reproducible teardown. Findings are backed by captured artifacts (endpoint, HTTP method, status code, byte size, host) and repro commands; where an observation was seen live but not retained as a file, §7 says so expli

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.