pgvector plus HNSW replaced Pinecone on half my side projects. The schema, the index picks, hybrid search with FTS, and where I still reach for…
I ran an LLM judge for six weeks before I noticed it kept rewarding longer answers. Here is the evaluation metrics stack I actually trust…
My honest take on Vercel AI SDK v5 after three production projects, plus the useChat and tool-calling gotchas I wish someone had warned me about…
I pointed a local 7B model at my Postgres database to write SQL from plain English. Here's where text-to-sql LLMs held up, where they lied,…
Real LLM hallucination examples from my own apps, why retrieval doesn't fully fix them, and the cheap code checks I run to catch made-up answers…
I almost shipped a phishing URL inside an AI-generated PR. Here are the AI code review tools and checks I now run before any AI-written…
Six months running Laravel AI in production: the stack I actually reach for, the package I bailed on, and the parts that are still mostly…
Why LLMs fail at spatial tasks isn't always about model size. The input format matters more than you'd expect, and here's what to do about…
New research shows LLM API testing misses how chatbots actually behave. Here's what the data says about the gap and how to fix your eval…