Manual Prompt Writing Beats Automated Agent Optimization, Dev Finds
BraceSproul · x · 2026-08-03
Developer Brace Sproul shared practical insights on prompt optimization, noting that humans are still crucially needed in the loop. While agents are useful for reading traces and running scripts, manual prompt writing often yields better results.
Sproul spent about three days trying to automate the optimization of the OpenWiki prompt using Codex via hill climbing, but eval scores barely increased. Switching to full manual mode, he made more progress in a few hours than the agent did in three days.
More from coding & agent
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16