My long-context RAG bot kept refusing questions whose answers were right there. The fix was in my anti-hallucination prompt, not my retriever.
I ran Claude's prompt caching in production for six months. Here's the cache_control setup, TTL trade-offs, and the anti-patterns that burned me.
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…
Fine-tune an LLM and a small open model can beat GPT-5 on a narrow task, cheaper. A look at when QLoRA wins, when it loses,…
Prompt engineering tunes what you ask. Context engineering decides what the model sees at all. Where my agents kept dying on long runs, and the…
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…
A new paper on autonomous programming found that separating code generation from debugging across models nearly doubled solved problems. Here's the takeaway.
A smarter model still writes the same broken first draft. What actually moved my output was wrapping a cheaper model in a feedback loop that…
I spent a month running local LLMs on my own GPU instead of an API. Here is where self-hosted models earned their place, and where…