Mixed Keyboard Shortcuts
TL;DR: A cheat sheet of keyboard shortcuts across tools.
Blog#
Vim Shortcuts
TL;DR: A cheat sheet of Vim commands and concepts.
FastAPI in 60 Minutes
TL;DR: Learn how to build a REST API with FastAPI and uvicorn in 60 minutes with hands-on examples covering request validation, dependency injection, and a complete Book Catalog API served over real HTTP
GitHub CLI Shortcuts
TL;DR: A cheat sheet of gh (GitHub CLI) commands for repos, issues, PRs, and
workflows.
TIL: Auto-Reload Files in Vim When Working With AI Agents
TL;DR A 3-line vimscript snippet that polls checktime every second keeps vim
buffers in sync when AI agents modify files on disk.
TIL: How to Not Let Coding Agents Commit Code Automatically
TL;DR Disable coding agents from committing code automatically. Use git
permission denies in .claude/settings.local.json to prevent auto-commits and
force a review-before-commit workflow.
My AI Policy
TL;DR: I use LLMs as human team members and despise AI slop
Markdown Viewers on macOS: Terminal and Browser Options
TL;DR: Render markdown from terminal using glow (for terminal viewing),
mdcat (for rich formatting), grip (for GitHub-accurate previews with
images), or pandoc (for document conversion and flexibility).
Rendering Markdown Files From Your Terminal with open_md.py
TL;DR: open_md.py is a flexible CLI tool that renders markdown files to HTML
using pandoc or grip, and can open them directly on GitHub or in your
browser, with support for embedded diagrams and both local and dockerized execution
How to Use OpenRouter with Simonw's LLM CLI
TLDR: A practical guide on using OpenRouter through Simon Willison's LLM CLI to access dozens of LLM models from a single terminal, including free tier options.
How to Use Claude Code with OpenRouter
TL;DR Learn how to configure Claude Code to route LLM calls through OpenRouter, enabling access to models from multiple providers through a single API.
What Is LLM Reasoning Effort and How Does It Affect Cost?
TL;DR: LLM reasoning effort settings (low, medium, high) affect how much compute a model allocates to internal reasoning, increasing total token consumption and cost, even when per-token pricing stays the same.
How to Count LLM Usage Costs
TL;DR Track your LLM API spending with open-source tools like ccusage and
OpenUsage to gain visibility into daily costs, model-level breakdowns, and usage
patterns.
How to Compare and Choose LLM Models
TL;DR Comparing LLMs across real benchmarks and use an efficiency metric that combines quality, cost, and speed to pick the right model for each task
LLM CLI in 30 mins
TL;DR: llm_cli is a lightweight CLI tool that applies LLM transformations to
text and code files. Use it to refactor code, improve docs, apply linting
rules, or run custom prompts on file chunks, all from shell without leaving
editor.
llm CLI in 30 minutes
TL;DR: Simon Willison's llm CLI turns any large language model into a
composable Unix tool you can pipe, script, and template from the terminal.
mdm, a Unified Markdown Manager for Agent Skills
TL;DR: mdm unifies management of research ideas, blog posts, and Claude Code
skills across multiple repositories into one powerful command-line tool.
Python Code Coverage In 30 Mins
TL;DR: Python code coverage measures how much of your source code is tested, helping you improve test quality.
CausalML in 60 Minutes
TL;DR: Learn how to estimate heterogeneous treatment effects using CausalML in 60 minutes with hands-on examples including individual-level causal inference on CDC diabetes health data.
BambooAI in 60 Minutes
TL;DR: Learn how to build intelligent data analysis systems with BambooAI in 60 minutes with hands-on examples covering multi-agent workflows, dataframe analysis, and dynamic code generation.
TorchRL + PettingZoo MPE in 60 Minutes
TL;DR: Build a reproducible multi-agent reinforcement learning (MARL) pipeline using TorchRL and PettingZoo's multi-agent particle environment (MPE), train using centralized training, decentralized execution (CTDE), and verify that communication is meaningful using structured diagnostics and causal ablations.
How to Connect Claude Code Securely to Gmail
TL;DR: Connect Claude Code to Gmail in minutes using MCP: no passwords in prompts, no custom backend, just clean OAuth and Smithery.
AutoGen in 60 Minutes
TL;DR: Learn how to build agentic AI systems using AutoGen in 60 minutes with hands-on examples including live market data debates and SEC filing analysis.
TensorFlow in 60 Minutes
TL;DR: Learn how to build machine learning models using TensorFlow in 60 minutes with hands-on examples including neural networks and structural time series forecasting.
Python Package Tools in 30 mins
TL;DR: Comprehensive guide to Python package managers and virtual environment
tools, from pip and venv to modern alternatives like Poetry and uv.
UV in 30 mins
TL;DR uv is a very fast Python package manager written in Rust that replaces
pip, pip-tools, and virtualenv with a single tool that is 10-100x faster.
Ripgrep in 30 mins
TL;DR ripgrep is a blazingly fast search tool that combines the usability and
speed.
Welcome to Our Blog
TL;DR: Welcome to our new blog where we'll share insights on AI research, machine learning, software engineering, and our experiences in academia and industry.