GPT-6 Astra hands-on: stunning at 3D, but coding still needs heavy prompting
majidmanzarpour · x · 2026-09-09
A user replying to Peter Yang reports a similar experience: GPT-6 Astra is amazing at Blender but struggles with coding tasks without a lot of prompting. The original thread sums up using GPT-6 Astra as a daily driver since launch — impressive at building 3D games/models, high-level strategy, and computer/browser use, but held back by two issues: it sometimes explains how it would do something instead of just doing it, plus another unspecified limitation.
Related event: GPT-6 Astra impresses in 3D but struggles with coding(2 posts)→
More from Models
- When will Clay Institute verify OpenAI's solution and pay the prize? — peterjliu · 2026-09-10
- GPT-6 shows 'incredible' physical-space instruction following on real robots, early tests show — k7agar · 2026-09-10
- Goodfire uses Ai2's open post-training stack to predict how training runs change model behavior — allen_ai · 2026-09-10
- Sebastian Raschka breaks down GPT-6 Astra rumors, looped transformers and hidden chains of thought — rhiever · 2026-09-10
- OpenAI responds to the math authorship dispute: Matthew Berman breaks it down — Matthew Berman · 2026-09-10
- GPT-6 Astra's no-CoT time horizon estimated at 8 minutes to 1 hour — OwainEvans_UK · 2026-09-10