User reports Astra is faster and more token-efficient, asks OpenAI what changed
McDonaghMatthew · x · 2026-09-21
Developer McDonaghMatthew reports that Astra has become noticeably faster and even more token-efficient, directly asking OpenAI "what did you do?"
The post includes a comparison, suggesting OpenAI quietly shipped server-side optimizations or changes to Astra without announcement.
More from Models
- Tobi Lütke: local Dell server runs DeepSeek 4.1 Flash at ~300 tok/s, a billion tokens a month — BLUECOW009 · 2026-09-21
- LLMs still struggle at niche-domain labeling: a cluster-then-LLM pipeline with brittle second-pass labels — FanaHOVA · 2026-09-21
- A "decide" Primitive: Browser On-Device AI as a Native JS Control Flow — cocktailpeanut · 2026-09-21
- Rumor: GPT-6 Sol Lands Tuesday, Internal 'Bel' Deemed AGI; Opus 5.5 May Drop Monday — imjustnewatai · 2026-09-21
- Jev underperforms: researchers find better alternatives to GLiNER2-class extractors — airesearch12 · 2026-09-21
- Nym rebuilds its agent around Jev, a fast classifier model, for speed and cost gains — moyix · 2026-09-21