Theo's Long Critique: GPT-6.2 Astra Is Painful to Use, Opus 5.5 Still Better Overall
Angaisb_ · x · 2026-11-18
This post relays Theo's article "Why I hate GPT-6.2 Astra." Theo says early testing frustrated him so much he spent a day writing a letter of complaint to OpenAI; the company fixed a handful of issues but not enough. His verdict: GPT-6.2 Astra is extremely annoying to work with, and Opus 5.5 remains the better model overall. The poster laments that OpenAI can't seem to ship a great model nobody complains about.
More from Models
- Microsoft's MAI Models Go Live on Copilot, OpenRouter and Vercel — marlene_zw · 2026-11-18
- GPT-6.2 Astra Is Now Out — nevrekaraishwa2 · 2026-11-18
- Researcher: guidance is underrated and works for weak models — in any space — churchkey · 2026-11-18
- Every Tests OpenAI's New Astra and Sol Models on Coding, Writing and Creative Work — danshipper · 2026-11-18
- Ethan Mollick: GPT-6.2 Is OpenAI's First Frontier Release Since GPT-4.5 That Isn't a Clear Step Forward — emollick · 2026-11-18
- banteg benchmarks GPT 6.2 Sol and Astra debut on his puzzle eval — banteg · 2026-11-18