Artificial Intelligence 6
- EmbeddingGemma 2 and Qwen3-Embedding vs bge-m3: Why I Kept bge-m3
- Why I Kept My Own LLM Gateway over LiteLLM and 9Router
- The GIL Bottleneck Hiding in Self-Hosted LLM Serving
- Open-weight LLMs are winning on cost, not benchmarks
- How LLM Reasoning Actually Works, and When It Is Not Worth Paying For
- Reliable Structured Output from LLMs: Schemas, Tool Calling, and Repair Loops