Thread

OpenSpec – A lightweight and configurable AI spec framework

204 points · 100 comments · etoxin

sheepscreek · 1789606644 · focus · HN ↗
Haven’t we moved on from these things? Most recent LLMs have been trained on enough long context tasks to have become pretty good at planning. Perhaps with contributions from the harness. In either case, I wouldn’t bother if I were using Codex or Claude Code.
1. loveparade · 1789618953 · focus · HN ↗
  That's what I thought too. I used speckit quite a bit before and I've had mixed results at best. You are just moving ambiguity and code review from one place to another without really gaining anything.
  1. visarga · 1789620279 · focus · HN ↗
    I just rely on a log of user messages, all messages the user typed in a project as raw data and do a pass with agents to synthesize intent. Then use this for planning and validation of code. I think the user messages are the most valuable data in a project for this reason. Doing this reflection pass on messages takes just a few minutes even for thousands of messages. It keeps global perspective which is often lost in local work.

Unofficial Hacker News client; not affiliated with Y Combinator.