Dev loves Google's Astra for coding while others ditch it: model preferences puzzle labs
lucasmeijer · x · 2026-09-09
Developer Lucas Meijer notes a striking split in coding-model reception: he's very happy using Google's Astra for coding, while many others dislike it so much they've gone back to previous models. He muses that labs must have a ton of work ahead to figure out why the same model produces such divergent experiences — a reminder that personal workflow and task fit can matter far more than benchmarks suggest.
More from Models
- OpenAI's 11-day-trained model and ~10,000 coordinating agents cracked Navier–Stokes — peterwildeford · 2026-09-09
- Grok on AI cracking Navier-Stokes: not surprising, AI stood on giants' shoulders — robleclerc · 2026-09-09
- GPT-6 Astra tops Andon Labs' Vending-Bench, unseating Fable — Outside-Iron-8242 · 2026-09-09
- OpenAI: training new internal model with 'unprecedented' math benchmark performance — TheZvi · 2026-09-09
- DeepSeek v4.1 Flash flash sale: 58M tokens for $1, available for 2 days only — MicahBerkley · 2026-09-09
- OpenAI's Noam Brown: in a year, everyone will have AI that can tackle Millennium Prize Problems — Neurogence · 2026-09-09