‹ BackHN Continuity

Thread

OpenSpec – A lightweight and configurable AI spec framework

204 points · 100 comments · etoxin

  1. sheepscreek · · 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. virgil_disgr4ce · · focus · HN ↗
      specifying is not planning
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.