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.
More from coding & agent
- Auto-approving PRs: Qodo's rules-based workflow handles the coding-agent PR bottleneck — omarsar0 · 2026-11-18
- Record your judgment process 3 times, let AI build business evals from it — alliekmiller · 2026-11-18
- GPT-6.2 Sol hits 54.7 on Bug Hunt for $7, matching Fable 5.2 at 6% of the cost — PawelHuryn · 2026-11-18
- HF releases RL-trained Qwen3.8 adapter for opencode: +16pts on SWE-bench Pro, 8x fewer tokens — LysandreJik · 2026-11-18
- Noodle: Free open-source Mac app runs collaborative personal AI agents locally — Dave_Maynor · 2026-11-18
- Top engineers have stopped reading code: specs and tests become the persistent artifact — ZeeshanZiaML · 2026-11-18