Early user: gpt-6 astra follows instructions far better than 5.6-sol, no more tangents
haider1 · x · 2026-09-20
An early user reports that gpt-6 astra (md) follows instructions significantly better than 5.6-sol-md and no longer gets lost in endless second-guessing or random tangents.
The author is now eagerly awaiting gpt-6 sol and luna variants, noting that if they land at 5.6 sol/luna pricing, the result would be both faster and cheaper — a major win for heavy users.
More from Models
- User burns 100M tokens on Jev without exhausting the $5 free credit — DeryaTR_ · 2026-09-20
- Users slam Codex 'reset culture': paid subscribers hoard usage waiting for free resets — TheMoonMidas · 2026-09-20
- Andrew Chen: 400x cheaper inference could unlock ad-supported free AI-native apps — andrewchen · 2026-09-20
- Bilibili's AI Infinite Arena: 190 videos stress-testing 100+ models on real tasks — vista8 · 2026-09-20
- Users report suspiciously generous usage: full morning of building leaves 78% quota left — TheMoonMidas · 2026-09-20
- Researcher flags severe LLM degradation as a mission-critical concern — doodlestein · 2026-09-20