Last time I wrote about the judge that scores my benchmark, I left one thing out. That post was about adding a model to the scoring. It was not about the fact that the model is the…
Last time I wrote about my benchmark (the code that kills your browser), I skipped the boring part. Sixteen models, six attempts each, one task – that is 96 HTML files somebo…
After Anthropic’s recent moves – higher prices, hard-trimmed limits – a question I keep hearing more and more comes back: “Codex or Claude Code?”. And…
Recently I was messing around with the Refio plugin and testing it on local LLM models. In theory everything worked: the model was supposed to get the whole project context –…
There’s a moment when the model returns code, the file opens, and for two seconds you think it works. Sometimes it actually does. Other times the browser tab goes blank, or y…
I’m building a benchmark of local models. Simple task: build a Todo App in a single HTML file – add, delete, mark as done, filters, localStorage. Trivial. Each model ge…
Genuinely practical RAG? It’s not just about building a vector index and hoping the LLM will find everything on its own. When you’re working on a project, you’re …