Thread

1. 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. philipp-gayret · 1789630662 · focus · HN ↗

      I agree but your taste in making solutions, or that of your organisation may be very different from what an LLM does by default. I personally use specs to capture this taste; an example shared by most LLMs is that they like to document not only what they have built but also what they have not built. Especially after changing solutions or small migrations. Specifications can resolve most if not all of that behaviour.

Unofficial Hacker News client; not affiliated with Y Combinator.