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.
| """ | |
| This is a Python implementation of the WinRAR Keygen originally written in C++. | |
| Original Repository: https://github.com/bitcookies/winrar-keygen | |
| Developer: adasThePrime (https://github.com/adasThePrime) | |
| License: MIT | |
| DISCLAIMER: | |
| This software is provided for educational and authorized purposes only. |
Stop chasing Windows 11 alternatives or experimenting with risky third-party builds to upgrade from Windows 10 or trying to debloat mainstream editions. The ideal solution is already available: Windows 11 IoT LTSC.
It's a lightweight, stable, and bloat-free edition of Windows 11 that's perfect for productivity, development, or even gaming without the unnecessary apps, ads, or forced updates found in mainstream editions. Best of all, if your PC runs Windows 10 well, it'll handle Windows 11 IoT LTSC just as smoothly, with no performance drop or compatibility issues.
In this guide, I'll walk you through everything you need to know about Windows 11 IoT LTSC: how to prepare your system, install the OS, and configure it for daily use. By the end, you'll have a streamlined Windows setup perfect for productivity, development, or even gaming without the baggage of mainstream editions.
At the time of writing, the latest releas
| #!/usr/bin/env bash | |
| set -Eeuo pipefail | |
| RED=$'\033[1;31m' | |
| YELLOW=$'\033[1;33m' | |
| RESET=$'\033[0m' | |
| for arg in "$@"; do | |
| # Reject any non-ASCII byte. | |
| if LC_ALL=C printf "%s" "$arg" | grep -q "[^ -~]"; then |
Cloudflare, the CDN provider, suffered a massive outage today. Some of the world's most popular apps and web services were left inaccessible for serveral hours whilst the Cloudflare team scrambled to fix a whole swathe of the internet.
And that might be a good thing.
The proximate cause of the outage was pretty mundane: a bad config file triggered a latent bug in one of Cloudflare's services. The file was too large (details still hazy) and this led to a cascading failure across Cloudflare operations. Probably there is some useful post-morteming about canary releases and staged rollouts.
| twitterCardCount = 5; | |
| function getNextTweets(count) { | |
| const nextTweets = [...document.querySelectorAll("[data-testid='cellInnerDiv']:not(:has(>.HiddenTweet)) [data-testid='tweet']:not([data-twc-used])")].slice(0, count); | |
| nextTweets.forEach(e => e.dataset.twcUsed = true); | |
| return nextTweets; | |
| } | |
| function setStyle(styleText) { | |
| let styleEl = document.querySelector(".twc-style"); |
- Turn on the feature.
- Go to your safehouse/a festival.
- While in there, navigate to the garage tab.
- Open "Designs and paints".
- Click on "Paint Car" (if you've applied a livery made by another player before, it must go away first).
- Select some intensity (the slider or the value box).
- Change the color of your car.
- Your car should now glow.
| ID: 28; Name: RockOutA | |
| ID: 46; Name: RockOut_B | |
| ID: 19; Name: Number1 | |
| ID: 47; Name: RollBack | |
| ID: 8; Name: ClassicalDance | |
| ID: 33; Name: BestFriend | |
| ID: 3; Name: BlowKiss | |
| ID: 0; Name: BodyPop | |
| ID: 34; Name: BringIt | |
| ID: 35; Name: CantHearYou |
Hi fellow reader,
I'm ririxi, core maintainer of spicetify. Some people asked me to do a technical explanation of what spotify shipped with macOS Intel versions. This would be my first time writing a post like this, so I apologize for any inscriptions.
Spotify under the hood uses CEF (Chromium Embedded Framework) which is a framework around chromium, essentially electron but for C++. Chromium uses a V8 which is a Javascript engine created by Google. V8 can generate serialized representation (bytecode) of the V8 engine's heap. It contains pre-initialized JavaScript objects and functions.