Dev critique: GPT models' strict instruction-following kills productivity; astra gets stuck in self-blocking loops

kevinkern · x · 2026-11-18

The author argues criticism of astra and sol is louder now only because opus 5.5 and fable 5.2 offer a direct comparison — "we're spoiled and don't want to go back." GPT models follow instructions so strictly they stop over minor details and flag every little issue, hurting productivity and ruling them out as a main model. Astra's biggest issue is an unrecoverable self-blocking state: it builds everything around the thing you actually want, but not the thing itself, or needs constant nudging to continue.

He still uses sol for non-time-sensitive coding, astra for code reviews (where opus may wave things through), and terra 6.1 for app/browser testing — hoping OpenAI catches up and makes its models fun again.

Original post →

More from coding & agent

coding & agent channel →