Dev tries Opus 5.5, finds it needs heavy prompt iteration, doubles his bill, goes back to Fable 5.1
bindureddy · x · 2026-09-26
Developer Bindu Reddy tested Opus 5.5 and found it requires far more prompt iteration than Fable to get comparable results, doubling his bill and eating his time. He's switching back to Fable 5.1.
A first-hand reminder that newer models aren't automatically cheaper or easier: prompt-engineering overhead is a real cost in model selection.
More from coding & agent
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Claude Opus 5.5 runs an architecture search and finds AttnRes-Canon, a new top Transformer design — SonglinYang4 · 2026-11-11
- 5 research habits worth knowing: read papers backwards, reproduce first, wire coding agents via MCP — cneuralnetwork · 2026-11-11
- 'Adam can now do CAE': AI agent showcase in engineering simulation draws buzz — burhop · 2026-11-11