Stories by nicola_alessi

Ask HN: Opus 4.7 – is anyone measuring the real token cost on agentic tasks?

More tokens, less cost: why optimizing for token count is wrong

Show HN: Focused input cuts LLM output tokens by 63% bench on CC with FastAPI

Show HN: 58% cost by replacing file reads with a dependency graph on AI Coding

Ask HN: Why do AI coding agents refuse to save their own observations?

Show HN: Vexp – Your AI coding agent forgets everything. Mine doesn't

Show HN: Vexp – Local-first context engine for AI coding agents

Show HN: Vexp – graph-RAG context engine, 65-70% fewer tokens for AI agents

Is Entertainment Discovery Fundamentally Broken?

An experiment in mood-based movie discovery: Lumigo.tv

A Scalable Standard for Clean ECommerce Data in LLMs (Fork of Llms.txt)

Site-Llms.xml – An XML Sitemap Standard for AI-Friendly ECommerce Data