Dev loses a day of benchmarks to Claude Opus 5, begs for Opus 4.5 back
julianharris · x · 2026-09-18
Developer Julian Harris complains that Fable 5.1 burned through his Max 20 quota in one day, forcing him back to Opus 5, which he says finds "spectacular depths of incompetence" daily.
The breaking point: while migrating from Gemini to TypeSafe, the model created entirely new prompts, breaking apples-to-apples comparison and invalidating a full day of benchmarks and probability sweeps. He asks for Opus 4.5 back – a data point on real-world coding model frustration.
More from coding & agent
- Claude Code 2.1.275 ships 96 CLI changes, adds send-now shortcut and secret stripping — ClaudeCodeLog · 2026-09-18
- Dosu Cut Agent Debugging Time 90% Using Logfire MCP Across 697k+ Runs — samuelcolvin · 2026-09-18
- Pydantic Logfire's Sleeper Feature: Every Trace Is Just a Row in a Postgres Table — samuelcolvin · 2026-09-18
- Underrated MCP Use: Giving Coding Agents Like Claude Code Real Production Telemetry — samuelcolvin · 2026-09-18
- Jev Ditches Autoregression: A Model That Only Outputs Structured Decisions — karminski3 · 2026-09-18
- skilled-proposer v0.2.0 adds journaling: giving GEPA's reflection model memory of tried proposals — dbreunig · 2026-09-18