Dev observes Fable 5.2 is making design decisions closer to his own than Opus 5.5
adonis_singh · x · 2026-11-14
Developer adonissingh notes that model taste is slowly improving: Fable 5.2 is making more design decisions he would make himself, calling it "a good but hard-to-measure improvement over Opus 5.5."
A first-hand observation that subjective design judgment is becoming a new dimension for evaluating coding models.
More from coding & agent
- Ford dealership veteran pays for an AI system doing the work of 12 salespeople — aryanXmahajan · 2026-11-14
- One prompt gets AI to integrate WebMIDI so you can play your MIDI keyboard in the browser — alexanderchen · 2026-11-14
- Static model routers fail on long tasks — routing must be a dynamic handoff policy, dev argues — petrusenko_max · 2026-11-14
- MIT CSAIL Shares Programmer Wisdom: "There's Already a Library for That" — MIT_CSAIL · 2026-11-14
- OpenAI's Decisions API is underrated: dev builds ADHD detector, email triage and expense classifier — craigsdennis · 2026-11-14
- Open-Source Agent Workcell: Claude Code as an Autonomous Knowledge-Exploring Agent — Shivam__kumar · 2026-11-14