peterc’s gists

JonnyBurger / gist:5b801182176f1b76447901fbeb5a84ac

Created January 20, 2026 14:52

Claude Code Session


	╭─── Claude Code v2.1.12 ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
	│ │ Tips for getting started │
	│ Welcome back Jonny! │ Run /init to create a CLAUDE.md file with instructions for Claude │
	│ │ │
	│ │ ───────────────────────────────────────────────────────────────── │
	│ ▐▛███▜▌ │ Recent activity

sergeyk / claude_code_prompts_and_tools.yaml

Last active January 16, 2026 03:43

Claude Code System Prompt and Tool Descriptions

	model: claude-opus-4-20250514
	messages:
	- role: user
	content:
	- type: text
	text: \|
	<system-reminder>
	As you answer the user's questions, you can use the following context:
	# important-instruction-reminders
	Do what has been asked; nothing more, nothing less.

abacaj / train.py

Last active December 3, 2025 10:10

extending GRPOTrainer to run gsm8k eval during training

	import tqdm
	import numpy as np
	import torch
	import torch.distributed as dist
	import transformers

	def extract_xml_answer(text: str) -> str:
	answer = text.split("<final_answer>")[-1]
	answer = answer.split("</final_answer>")[0]
	return answer.strip()

willccbb / grpo_demo.py

Last active January 24, 2026 08:12

GRPO Llama-1B

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

kmorrill / gist:898579c18df24ac5094f691cd411d741

Created December 2, 2024 03:06

	We're going to create a preset patch using this guide.

	Technical Specification for OP-XY Patch JSON File Format

	1. Introduction

	1.1 Purpose
	The purpose of this document is to provide a comprehensive technical specification for the JSON file format used to store and exchange patch data on the OP-XY device. This specification aims to standardize the structure and content of patch files, ensuring compatibility and consistency across different patches, whether they are synth presets, drum kits, or sample-based instruments. By adhering to this format, developers, sound designers, and users can create, modify, and share patches efficiently and reliably.

	1.2 Overview

dhh / linux-setup.sh

Last active December 19, 2025 08:57

linux-setup.sh

	# THIS LINUX SETUP SCRIPT HAS MORPHED INTO A WHOLE PROJECT: HTTPS://OMAKUB.ORG
	# PLEASE CHECKOUT THAT PROJECT INSTEAD OF THIS OUTDATED SETUP SCRIPT.
	#
	#

	# Libraries and infrastructure
	sudo apt update -y
	sudo apt install -y \
	docker.io docker-buildx \
	build-essential pkg-config autoconf bison rustc cargo clang \

yunruse / yt.py

Last active June 14, 2024 04:20

very basic YouTube-to-RSS extractor

	#!/usr/bin/env python3

	# pip install scrapetube

	# for basic operation, use `python -m http.server --cgi`
	# and access /cgi-bin/yt.py?c={CHANNEL_ID}

	# Note that due to scrapetube limits, dates are fetched as eg "3 days ago"
	# so the further in the past a video is, the less precise the date will be.

levelsio / gist:5bc87fd1b1ffbf4a705047bebd9b4790

Last active January 9, 2026 15:38

Secret of Monkey Island: Amsterdam (by @levelsio) or how to create your own ChatGPT image+text-based adventure game

	# 2023-11-27 MIT LICENSE

	Here's the open source version of my ChatGPT game MonkeyIslandAmsterdam.com.

	It's an unofficial image+text-based adventure game edition of Monkey Island in Amsterdam, my home town.

	Please use it however you want. It'd be nice to see more ChatGPT-based games appear from this. If you get inspired by it, please link back to my X https://x.com/levelsio or this Gist so more people can do the same!

	Send me your ChatGPT text adventure game on X, I'd love to try it!

elesiuta / conway_chess.py

Last active December 26, 2025 00:22

Conway's Game of Chess (moved to https://github.com/elesiuta/conways-game-of-chess)

adrienbrault / llama2-mac-gpu.sh

Last active April 8, 2025 13:49

Run Llama-2-13B-chat locally on your M1/M2 Mac with GPU inference. Uses 10GB RAM. UPDATE: see https://twitter.com/simonw/status/1691495807319674880?s=20

	# 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

Peter Cooper peterc