geoffreylitt

name	explain-diff-html
description	Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.

Explain Diff

Please make me a rich, interactive explanation of the specified code change.

It should have these sections:

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.

greenstevester

April 2026 TLDR setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive

April 2026 TLDR Setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon)

Prerequisites

• Mac mini with Apple Silicon (M1/M2/M3/M4/M5)
• At least 16GB unified memory for Gemma 4 (default 8B)
• macOS with Homebrew installed

hamelsmu

Question: Should I avoid using RAG for my AI application after reading that "RAG is dead" for coding agents?

Many developers are confused about when and how to use RAG after reading articles claiming "RAG is dead." Understanding what RAG actually means versus the narrow marketing definitions will help you make better architectural decisions for your AI applications.

Answer: The viral article claiming RAG is dead specifically argues against using naive vector database retrieval for autonomous coding agents, not RAG as a whole. This is a crucial distinction that many developers miss due to misleading marketing.

RAG simply means Retrieval-Augmented Generation - using retrieval to provide relevant context that improves your model's output. The core principle remains essential: your LLM needs the right context to generate accurate answers. The question isn't whether to use retrieval, but how to retrieve effectively.

For coding

Olshansk

# A one liner to leverage the GPU on a mac to transcribe audio files
# Inspired by https://simonwillison.net/2024/Aug/13/mlx-whisper/
llm_transcribe_recording () {
	local file_path="$1"
	python3 -c "
import mlx_whisper
result = mlx_whisper.transcribe('$file_path', path_or_hf_repo='mlx-community/distil-whisper-large-v3')
print(result['text'])
"
}

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

adrienbrault

# Clone llama.cpp
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp

# Build it
make clean
LLAMA_METAL=1 make

# Download model
export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin

oneryalcin

# I couldn't get return generators from chains so I had to do a bit of low level SSE, Hope this is useful
# Probably you'll use another Vector Store instead of OpenSearch, but if you want to mimic what I did here, 
# please use the fork of `OpenSearchVectorSearch` in https://github.com/oneryalcin/langchain


import json
import os
import logging
from typing import List, Generator

python273

import os
os.environ["OPENAI_API_KEY"] = ""

from flask import Flask, Response, request
import threading
import queue

from langchain.chat_models import ChatOpenAI
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.schema import AIMessage, HumanMessage, SystemMessage

wuputah

Hydra Performance Microbenchmark

Important: This microbenchmark is not intended to represent any real workload. Compression ratios, and therefore performance, will depend heavily on the specific workload. This is only for the purpose of illustrating a "columnar friendly" contrived workload that showcases the benefits of columnar.

Schema