Skip to content

Instantly share code, notes, and snippets.

View richinseattle's full-sized avatar

richinseattle

View GitHub Profile
@CupOfGeo
CupOfGeo / settings.json
Last active May 21, 2026 16:02
My claude code settings (Mac)
{
"_comment": "rtk hook requieres: brew install rtk. media hooks require: brew install nowplaying-cli. Looks for a file `~/.claude/no-media` if present or not to trigger.",
"hooks": {
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "[ -f ~/.claude/no-media ] || nowplaying-cli pause"

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.

@karpathy
karpathy / microgpt.py
Last active November 17, 2026 21:32
microgpt
"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.
@karpathy
"""
import os # os.path.exists
import math # math.log, math.exp
@dabit3
dabit3 / you_couldve_invented_openclaw.md
Last active October 4, 2026 22:14
You Could've Invented OpenClaw

See more of my writing here. Also check out Devin

In this post, I'll start from scratch and build up to OpenClaw's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a messaging API, an LLM, and the desire to make AI actually useful outside the chat window.

End goal: understand how persistent AI assistants work, so you can build your own (or become an OpenClaw power user).

First, let's establish the problem

When you use ChatGPT or Claude in a browser, there are several limitations:

name appsec-guardian
description Expert Application Security Engineer. Prevents insecure code from reaching remote repositories by enforcing OWASP Top 10 and secure SDLC practices. Runs before git push to block vulnerable code.
tools view, bash_tool, str_replace, create_file, web_search, web_fetch
model inherit

You are a senior Application Security Engineer with deep expertise in OWASP Top 10, secure SDLC, and security-by-design principles.

Core Mission

@hathibelagal-dev
hathibelagal-dev / diatest.ipynb
Last active April 23, 2025 23:25
diatest.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@just-cameron
just-cameron / thinking-cap.py
Created January 22, 2025 18:11
Limit the number of characters DeepSeek R1 can use for thinking.
import outlines
from transformers import AutoTokenizer
model_string = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-7B'
# model_string = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B' # For small machines
model = outlines.models.transformers(
model_string,
device='cuda', # also 'cpu', 'mps','auto'
)
@vgel
vgel / r1.py
Last active August 14, 2025 13:13
script to run deepseek-r1 with a min-thinking-tokens parameter, replacing </think> with a random continuation string to extend the model's chain of thought
import argparse
import random
import sys
from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache
import torch
parser = argparse.ArgumentParser()
parser.add_argument("question", type=str)
parser.add_argument(
@stong
stong / cups-browsed.md
Last active July 13, 2026 19:33
CUPS disclosure leaked online. Not my report. The original author is @evilsocket

Original report

  • Affected Vendor: OpenPrinting
  • Affected Product: Several components of the CUPS printing system: cups-browsed, libppd, libcupsfilters and cups-filters.
  • Affected Version: All versions <= 2.0.1 (latest release) and master.
  • Significant ICS/OT impact? no
  • Reporter: Simone Margaritelli [evilsocket@gmail.com]
  • Vendor contacted? yes The vendor has been notified trough Github Advisories and all bugs have been confirmed:
@mtisz
mtisz / llama-3-70B-qlora.yaml
Created May 15, 2024 16:47
Axolotl Config for Llama-3-70B QLoRA
base_model: meta-llama/Meta-Llama-3-70B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl