More or less up-front planning in the AI era? Two camps argue it out
housecor · x · 2026-11-21
housecor poses the core question: in the AI coding era, should you do more or less up-front planning?
- For more planning: careful planning makes the agent more likely to one-shot the solution, saving tokens, time, and money.
- For less planning: tokens are cheap so rework is cheap; planning delays user feedback; AI is fast enough to try many ideas quickly.
In replies, mattpocockuk adds that rework is still frustrating even with AI and his time feels more constrained than ever, so AI-assisted time must feel effective. housecor counters that re-prompting from scratch now takes less time than building once did previously. mattpocockuk then scopes his position: up-front planning only matters when rework is costly (large diffs and features); if rework is cheap, it's unnecessary.
Related event: Debate Sparks Over How Much Planning AI-Era Developers Should Do(3 posts)→
More from coding & agent
- Multica Ships Realtime Docs for 100+ Humans and Agents, Replacing Feishu Internally — jiayuan_jy · 2026-11-21
- Epic Ports 20,000+ Fortnite Blueprints to Verse in Two Weeks with AI, Expected to Take Years — jradoff · 2026-11-21
- Merchant blocks shopping agent, loses $1,100 sale as bot buys locally instead — Scobleizer · 2026-11-21
- Threat actor Storm-3358 uses Hermes agent framework with skills that train AI to evade SOC detection — cyb3rops · 2026-11-21
- Matt Pocock narrows his claim: up-front planning only for costly, large rework — mattpocockuk · 2026-11-21
- housecor: re-prompting from scratch now beats building it once the old way — housecor · 2026-11-21