🎡 HK Playground 🎢
Posts
- How much does quantization hurt an LLM? 8-bit vs 4-bit, tested
- nohup vs tmux: how to keep a Python job running after SSH disconnects
- Before benchmarking free-threaded Python, check what NumPy already does
- Your RAG documents are data, not instructions—and not automatically true
- How do you evaluate LLM answers? Exact match vs key facts vs LLM-as-judge
