« I don’t write prompts anymore. I build loops. » Several major figures in AI have been repeating some version of this sentence for a few months now, and it’s worth pausing on. Boris Cherny, the creator of Claude Code, explained in an interview that he barely writes prompts himself anymore. His work now consists of building…
RAGAS and DeepEval both score RAG systems: faithfulness, context precision, contextual relevancy. The metrics overlap 80%. What separates them is where and how you use them. RAGAS was born from a research paper. DeepEval was born from a CI/CD need. It shows in both APIs, and it determines which one you should install first. On…
You want to fine-tune an LLM. Chances are, you don’t need to. There’s a trap that almost every developer falls into the first time they explore fine-tuning. They see an LLM that doesn’t know their product, their terminology, or their brand voice. So they start looking for ways to adapt it. They come across fine-tuning….
I used to think vector search was enough.
It isn’t.
Embeddings capture the overall meaning of a text, not its fine-grained requirements.
And when you search for ** »React Senior Paris »** and get ** »React Junior Lyon »** as the top result, that’s exactly the problem: a search engine that understands the domain, but not the actual query.
I wrote a deep dive on the **Retrieve → Re-rank** pipeline: why Dense Retrieval alone eventually hits its limits, how Cross-Encoders fix the problem, and how the two work together in modern RAG architectures.