Dev: with latest-gen LLMs he stops overspecifying and lets the model riff
jongranskog · x · 2026-11-09
Developer jongranskog shares a shift in his prompting habits: with previous LLM generations he worked hard to overspecify and fence in problem descriptions to prevent mistakes; with the latest generation he often prefers leaving things open so the model can add to his ideas — a sign of how rising capability changes prompt strategy.
More from coding & agent
- People are vibe coding synthesizers now — AI-built synths are a thing — billyjhowell · 2026-11-09
- Dev builds free browser tycoon game Mall Bats with Claude writing nearly all the code — jacobjr23 · 2026-11-09
- Open-Source Mac Status Light App Monitors Multiple Claude Code Sessions — stateofteddy · 2026-11-09
- Researcher builds hardest-ever RCE chain largely AI-driven with GLM — banteg · 2026-11-09
- Dad and kids build a playable Roblox game with zero code using Claude, MCP and Tripo — minchoi · 2026-11-09
- You can still spot a vibecoded site in 2 seconds, even with Opus 5.5 — hewarsaber · 2026-11-09