Harim Choihttps://harimxchoi.com/writing/Writing by Harim ChoiWarpQuant: Dual-Domain Low-Bit LLM Quantizationhttps://harimxchoi.com/writing/warpquant-dual-domain-quantization/https://harimxchoi.com/writing/warpquant-dual-domain-quantization/Sun, 16 Aug 2026 00:00:00 GMTA post-training quantization method that reaches INT2/INT3 SOTA accuracy and runs the compressed weights directly through a C++/CUDA llama.cpp kernel — 7.36× faster decoding than GPTQ W3.When to Use What: The Missing Framework for Multi-Agent Competitive Systemshttps://harimxchoi.com/writing/multi-agent-competitive-systems/https://harimxchoi.com/writing/multi-agent-competitive-systems/Fri, 02 Jan 2026 00:00:00 GMTFour questions for choosing a method in competitive multi-agent problems such as sealed-bid auctions, ad bidding, and trading.Building a Production LangGraph Travel Agenthttps://harimxchoi.com/writing/production-langgraph-travel-agent/https://harimxchoi.com/writing/production-langgraph-travel-agent/Wed, 12 Nov 2025 00:00:00 GMTHow I built a LangGraph travel assistant that searches flights, hotels, and activities in parallel and assembles budget-aware packages.Modern Anti-Bot Systems and How to Bypass Themhttps://harimxchoi.com/writing/modern-anti-bot-systems/https://harimxchoi.com/writing/modern-anti-bot-systems/Sun, 09 Nov 2025 00:00:00 GMTAn engineering deep-dive into web scraping in 2025, with a production case study.