rohitg00

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

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.

gagarine

Reverse Mouse Wheel scroll in Windows 11

Chose between natural mode like MacOS or Windows default mode.

Step 1: Open Windows PowerShell in Administrator Mode.

You can do this by going to Start Menu, type PowerShell, and click Run as Administrator.

Step 2: Copy the following code and paste it in the command line of Windows PowerShell:

$mode = Read-host "How do you like your mouse scroll (0 or 1)?"; Get-PnpDevice -Class Mouse -PresentOnly -Status OK | ForEach-Object { "$($_.Name): $($_.DeviceID)"; Set-ItemProperty -Path "HKLM:\SYSTEM\CurrentControlSet\Enum\$($_.DeviceID)\Device Parameters" -Name FlipFlopWheel -Value $mode; "+--- Value of FlipFlopWheel is set to " + (Get-ItemProperty -Path "HKLM:\SYSTEM\CurrentControlSet\Enum\$($_.DeviceID)\Device Parameters").FlipFlopWheel + "`n" }

ourai

智勇大闯关第三季

8月20日，阿里校园招聘前端岗位的在线笔试将统一开始。在这之前，我们先玩一下热身赛吧！ http://ued.taobao.com/quiz3/ 截至8月18日11：00之前成功通关并且表现优异的同学，将有机会收到我们的惊喜邮件！

以上是阿里巴巴集团校园招聘的某一条微博的内容。

虽然我早已不是学生，本着好奇心也要玩一玩此游戏！经过几个小时的奋斗，我看到了美女，但不知道那是不是 True Ending。也许很多人把游戏通关之后就不玩不去探索了，可我不一样！我玩游戏向来都是要尽量把所有隐藏要素都挖掘出来才算结束。

正是因为知道结果，才有可能去优化过程，一个工程师的职责难道不正是这个么？“如何自动化、智能地去过每一关”的想法让我的血液稍微沸腾了起来。又经过几个小时的编码及测试，自我感觉已经把“隐藏要素”挖得差不多了。现将各个关卡的过关要点及自动获取过关条件的 JavaScript 脚本放出来。

karadaisy

import java.io.InputStreamReader;
import java.io.PrintStream;
import java.lang.reflect.Field;


public class AstToDot {

  /**
   * @param args
   * @throws Exception 

cuimuxi

import gevent
from gevent import monkey, queue

monkey.patch_all()

import urllib2
from time import sleep
import traceback
import logging

lotem

# luna_pinyin.custom.yaml
#
# 在【朙月拼音】裏使用Emoji表情（這份配置已過時，新的emoji實現代碼在 https://github.com/rime/rime-emoji ）
#
# 保存到Rime用戶文件夾後，重新部署生效
# ~/.config/ibus/rime  (linux)
# ~/Library/Rime       (macos)
# %APPDATA%\Rime       (windows)
#
# 如果目標文件已經包含其他修改內容，只需按照縮進合併 patch: 以下的部分

be5invis

<dict>
	<key>match</key>
	<string>[$*,£¥·‘“〈《「『【〔〖〝﹗﹙﹛＄（．［｛￡￥]*[&#x3000;-&#x9fff;][!%),.:;>?¢¨°·ˇˉ―‖’”„‟†‡›℃∶、。〃〆〈《「『〕〗〞︵︹︽︿﹃﹘﹚﹜！＂％＇），．：；？］｀｜｝～ヽヾーァィゥェォッャュョヮヵヶぁぃぅぇぉっゃゅょゎゕゖㇰㇱㇲㇳㇴㇵㇶㇷㇸㇹㇺㇻㇼㇽㇾㇿ々〻]*</string>
	<key>name</key>
	<string>meta.cjkword</string>
</dict>

scotu

.highlight { background-color: #ffffcc }
.highlight .c { color: #586E75 } /* Comment */
.highlight .err { color: #93A1A1 } /* Error */
.highlight .g { color: #93A1A1 } /* Generic */
.highlight .k { color: #859900 } /* Keyword */
.highlight .l { color: #93A1A1 } /* Literal */
.highlight .n { color: #93A1A1 } /* Name */
.highlight .o { color: #859900 } /* Operator */
.highlight .x { color: #CB4B16 } /* Other */
.highlight .p { color: #93A1A1 } /* Punctuation */

huyng

### MATPLOTLIBRC FORMAT

# This is a sample matplotlib configuration file - you can find a copy
# of it on your system in
# site-packages/matplotlib/mpl-data/matplotlibrc.  If you edit it
# there, please note that it will be overridden in your next install.
# If you want to keep a permanent local copy that will not be
# over-written, place it in HOME/.matplotlib/matplotlibrc (unix/linux
# like systems) and C:\Documents and Settings\yourname\.matplotlib
# (win32 systems).