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.

abadger

=======
Modules
=======

This is an in-depth dive into understanding how Ansible makes use of modules.
It will be of use to people working on the portions of the Core Ansible Engine
that execute a module, it may be of interest to people writing Ansible Modules,
and people simply wanting to use Ansible Modules will likely want to read
a different paper.

baraldilorenzo

##VGG19 model for Keras

This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

coderfi

from __future__ import print_function
from nanomsg import Socket, REQ, REP, PUB, SUB, DONTWAIT, \
                    NanoMsgAPIError, EAGAIN, SUB_SUBSCRIBE
import time
from gevent import monkey
import gevent

monkey.patch_all()

lukecampbell

import sys
import select
import gevent

def stdin_ready():
    infds, outfds, erfds = select.select([sys.stdin], [], [], 0)
    if infds:
        return True
    else:
        return False