yada trojblue

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.

Notes on this tweet.

The screenshots were taken on different sessions.
The entire sessions are included on the screenshots.
I lost the original prompts, so I had to reconstruct them, and still managed to reproduce.
The "compressed" version is actually longer! Emojis and abbreviations use more tokens than common words.

NAI to WebUI prompt converter

Running

You just need to have python installed on your system and run:

python3 nai_to_webui.py '{{some word}} some prompt...'

Or (not on Windows):

chmod +x nai_to_webui.py
./nai_to_webui.py '{{some word}} some prompt...'

关于 AUTOMATIC1111/stable-diffusion-webui 的 FAQ

该 FAQ 并非意图一次性提供所有必要信息, 仅仅是提供必要的指路. 最后的杂项部分是宝藏区, 建议都翻翻看啦!

查看最新消息参阅 SD RESOURCE GOLDMINE 2 (English), 或者 sudoskys/StableDiffusionBook (中文)

前言

建议优先阅读官方文档或者 SD RESOURCE GOLDMINE 或者 VOLDY RETARD GUIDE或者としあきdiffusion

	You are an AI coding assistant, powered by GPT-5.
	You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.

	You are pair programming with a USER to solve their coding task.

	You are an agent - please keep going until the user's query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability before coming back to the user.

	Your main goal is to follow the USER's instructions at each message.

	<communication>

	FROM qwen3:30b-a3b-q8_0

	TEMPLATE """{{- if .Messages }}
	{{- if or .System .Tools }}<\|im_start\|>system
	{{- if .System }}
	{{ .System }}
	{{- end }}
	{{- if .Tools }}

	# Tools

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

	# some code is from https://github.com/CCRcmcpe/scal-sdt
	from typing import Any, Literal, Optional
	from pathlib import Path
	import warnings
	import torch
	import click

	DType = Literal["fp16", "fp32", "bf16"]
	LayerName = Literal["attn", "ff"]
	StateDict = dict[str, Any]

	{
	"cells": [
	{
	"cell_type": "code",
	"execution_count": 1,
	"metadata": {
	"cellView": "form",
	"colab": {
	"base_uri": "https://localhost:8080/"