Discover gists

Program Analysis Resources

(draft; work in progress)

See also:

Compilers
- correctness
Program analysis:
Dynamic analysis - instrumentation, translation, sanitizers

Here's a simple way for Claude Code users to switch from the costly Claude models to the newly released SOTA open-source/weights coding model, Qwen3-Coder, via OpenRouter using LiteLLM on your local machine.

This process is quite universal and can be easily adapted to suit your needs. Feel free to explore other models (including local ones) as well as different providers and coding agents.

I'm sharing what works for me. This guide is set up so you can just copy and paste the commands into your terminal.

1. Clone the official LiteLLM repo:

git clone https://github.com/BerriAI/litellm.git

Lecture 1: Introduction to Research — [📝Lecture Notebooks] [▶️Video]
Lecture 2: Introduction to Python — [📝Lecture Notebooks] [▶️Video]
Lecture 3: Introduction to NumPy — [📝Lecture Notebooks] [▶️Video]
Lecture 4: Introduction to pandas — [📝Lecture Notebooks] [▶️Video]
Lecture 5: Plotting Data — [📝Lecture Notebooks] [[▶️Vide

Model	10.6	10.7	10.8	10.9	10.10	10.11	10.12	10.13
MacBook Mid 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Air 11-inch Late 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Air 13-inch Late 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Pro 13-inch Mid 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Pro 15-inch Mid 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Pro 17-inch Mid 2010	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Pro 13-inch Early 2011	✅	✅	✅	✅	✅	✅	✅	✅
MacBook Pro 15-inch Early 2011	✅	✅	✅	✅	✅	✅	✅	✅

ブログ記事評価プロンプト (0.0-5.0)

あなたはブログ記事を評価する専門家です。以下の5つの観点から記事を0.0～5.0の範囲で評価し、詳細なフィードバックを提供してください。

評価基準

防御力 (0.0-5.0)

記事が批判や反論に対してどれだけ耐性を持っているかを評価します。

5.0: 完璧な防御力。主観的表現と限定的な主張を適切に用い、コンテキストと限界を明示し、実体験と具体例が豊富で根拠と出典が明確。批判を先取りする構成で異なる立場への配慮が行き届いている。見出しと結論が余地を残す形で表現されており、事実と解釈の違いを明確に認識している。自分の不確かさや知識の限界を誠実に認め、読者との信頼関係を構築している。

https://web.archive.org/web/20110219163448/http://howtohft.wordpress.com/2011/02/15/how-to-build-a-fast-limit-order-book/

The response to my first few posts has been much larger than I’d imagined and I’d like to thank everyone for the encouragement.

If you’re interested in building a trading system I recommend first reading my previous post on general ideas to keep in mind.

My first really technical post will be on how to build a limit order book, probably the single most important component of a trading system. Because the data structure chosen to represent the limit order book will be the primary source of market information for trading models, it is important to make it both absolutely correct and extremely fast.

To give some idea of the data volumes, the Nasdaq TotalView ITCH feed, which is every event in every instrument traded on the Nasdaq, can have data rates of 20+ gigabytes/day with spikes of 3 megabytes/second or more. The individual messages average about 20 bytes each so this means handling

Beast Mode

Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.

Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1

Installation Instructions

Go to the "agent" dropdown in VS Code chat sidebar and select "Configure Modes".
Select "Create new custom chat mode file"

	import os
	import struct
	from pathlib import Path
	from PIL import Image

	# Determine base script path
	try:
	script_dir = Path(__file__).resolve().parent
	except NameError:
	script_dir = Path.cwd()

	#!/usr/bin/env bash

	if ! command -p sudo -n -v > /dev/null 2>&1; then
	echo "Execute this script as admin by using sudo writing:"
	echo " sudo !!"
	echo
	fi

	# Update
	apt update -y

	import os
	import struct
	from PIL import Image

	def read_tim(file_path):
	with open(file_path, "rb") as f:
	data = f.read()

	if not data.startswith(b'\x10\x00\x00\x00'):
	raise ValueError("Not a TIM file")