HN Explorer

nicola_alessi

↗ HN profile [ 56.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Ask HN: Opus 4.7 – is anyone measuring the real token cost on agentic tasks?

    Shipped today. The benchmarks are real: 87.6% SWE-bench (from 80.8%), +13% on coding tasks, 3x more resolved production tasks on Rakuten-SWE-Bench. But there are a few changes that compound on each other for token…

    1 points 0
  2. More tokens, less cost: why optimizing for token count is wrong

    I ran a controlled benchmark on AI coding agents (42 runs, FastAPI, Claude Sonnet 4.6) and found something that broke my mental model of LLM costs. The setup: I built an MCP server that pre-indexes a codebase into a…

    1 points 5
  3. Show HN: Focused input cuts LLM output tokens by 63% bench on CC with FastAPI

    I built an MCP server (vexp) that pre-indexes a codebase into a dependency graph and serves only relevant code to AI coding agents. While benchmarking it, I found something I wasn't looking for. The expected results…

    2 points 1
  4. Show HN: 58% cost by replacing file reads with a dependency graph on AI Coding

    I got tired of watching Claude Code read entire files when it needed one function. Built an MCP server that pre-computes a dependency graph with tree-sitter and serves only the relevant code nodes to the agent. Ran a…

    4 points 1
  5. 1 points 1
  6. Ask HN: Why do AI coding agents refuse to save their own observations?

    I've spent months building tooling for AI coding agents and hit something I can't fully explain. If you give an agent (Claude Code, Cursor, Codex) a tool to save observations — "save_observation: persist this insight…

    2 points 1
  7. Show HN: Vexp – Your AI coding agent forgets everything. Mine doesn't (vexp.dev)

    I built vexp because AI coding agents have two expensive problems: they waste tokens reading irrelevant code, and they forget everything between sessions. The token problem: agents read entire files linearly to build…

    1 points 0
  8. Show HN: Vexp – Local-first context engine for AI coding agents

    I built vexp to solve two problems I kept hitting with AI coding agents (Claude Code, Cursor, etc.): 1. Token waste: agents read entire files linearly to understand a codebase. On a medium TypeScript project, a single…

    1 points 0
  9. Show HN: Vexp – graph-RAG context engine, 65-70% fewer tokens for AI agents

    I've been building vexp for the past months to solve a problem that kept bugging me: AI coding agents waste most of their context window reading code they don't need. The problem When you ask Claude Code or Cursor to…

    3 points 0
  10. Is Entertainment Discovery Fundamentally Broken?

    For the last year, I've been obsessed with a problem: finding something to watch is a chore. The interfaces of Netflix, Prime, and others feel like slot machines designed for maximum engagement, not for matching my…

    2 points 4
  11. 1 points 0
  12. An experiment in mood-based movie discovery: Lumigo.tv (lumigo.tv)
    1 points 1
  13. 1 points 0
  14. 1 points 0
  15. 1 points 0
  16. 1 points 0
  17. 1 points 0
  18. A Scalable Standard for Clean ECommerce Data in LLMs (Fork of Llms.txt)

    The Problem: LLMs are terrible at understanding eCommerce sites. They: Hallucinate prices/specs from messy HTML Waste tokens on UI boilerplate (headers, popups, ads) Struggle with real-time inventory/pricing updates Our…

    2 points 1
  19. 2 points 1
  20. Site-Llms.xml – An XML Sitemap Standard for AI-Friendly ECommerce Data (github.com)

    We've forked Answer.AI's llms.txt to solve a specific problem: how eCommerce sites with 10K+ products can expose clean product data to LLMs without inefficient scraping. What it does: site-llms.xml is a machine-readable…

    1 points 4
  21. 1 points 0
  22. 1 points 0
  23. Ask HN: Why hasn't anyone fixed product search yet?

    Every solution I've seen either: 1. Replicates Google's ad-driven model (but worse) 2. Claims 'AI' but acts as a black box Yet we all waste hours daily on: - Decoding fake reviews - Reverse-engineering SEO-optimized…

    2 points 0
  24. 1 points 1
  25. 1 points 0