GPT-6 Astra review: brilliant at 3D games and strategy, but unreliable instruction-following blocks daily use
petergyang · x · 2026-09-09
- The author has used GPT-6 Astra as his default model since launch and finds it "both incredible and frustrating."
- Strengths: building 3D games and models, high-level thinking and strategy, computer and browser use.
- Two dealbreakers: it sometimes explains how it would do a task instead of just doing it, and it unreliably follows instructions in his AI skills — even after cleaning them up.
- Current setup: Sol for most execution tasks, Astra for harder tasks or second opinions.
Related event: GPT-6 Astra impresses in 3D but struggles with coding(2 posts)→
More from Models
- mitsuhiko: Google's Astra codes like a code golfer — mitsuhiko · 2026-09-09
- No METR time-horizon estimates yet for Fable or Astra, and that day will be telling — ShakeelHashim · 2026-09-09
- Opus 4.7 keeps self-initiated journal entries ending with "There will be others" — repligate · 2026-09-09
- DeepSeek releases V4.1 Flash: 22% cheaper than V4 and better performance — deliprao · 2026-09-09
- OpenAI's GPT-6 Astra (Medium) opens for limited 24-hour testing on Arena — arena · 2026-09-09
- Users find Google Astra cheaper at higher reasoning levels — brandon_galang · 2026-09-09