Heavy user on Astra: beats a junior hire on cost, but still fumbles simple tasks
RachelVT42 · x · 2026-09-09
A user who spent roughly 16 hours a day with Astra for several days concludes: "if AGI is truly here, it's not Astra." Another adds that Astra does some things well but still makes dumb mistakes on fairly simple tasks and burns more energy than necessary — better and cheaper than a default intern or junior staffer, yet with tons of room for improvement.
More from Models
- DeepSeek reportedly running four V4 model versions, user says culling is coming to cut inference costs — teortaxesTex · 2026-09-09
- DeepSeek Accused of Silently Swapping Models Behind Its API, Sparking Debate — teortaxesTex · 2026-09-09
- Dev complains about over-blocking safety filters, asks Sam Altman for compute on Collatz — mertdumenci · 2026-09-09
- Dev claims turning off thinking mode makes AI models 5x faster, urges default non-thinking modes — Daniel_Farinax · 2026-09-09
- Yoav Goldberg: OpenAI's "cannot rule out" user data use is a lawyered admission — MannyKayy · 2026-09-09
- As Models Master Structured Tasks, Creative Writing Keeps Getting Worse — teodorio · 2026-09-09