Dev who tested GPT-6.2 for weeks calls it 'utterly unusable' in public review
SEO · x · 2026-11-18
- Matt Shumer says he tested GPT-6.2 for weeks and found it 'utterly unusable,' linking his review.
- A widely-followed dev (SEO) replies describing a multi-model pipeline—Astra 6 for deep planning, fable 5.2 reviewing/tweaking in a loop, Opus 5.5 building—and asks whether to keep Astra 6 or step up to 6.2 for the planner role.
- The substance: a notable developer's harsh hands-on verdict on the new frontier model, plus a multi-model orchestration workflow.
More from Models
- Noam Brown's first take on Astra 6.2: expect math breakthroughs within weeks — polynoamial · 2026-11-18
- Google set to release another Gemini model, targeting Anthropic over OpenAI — kimmonismus · 2026-11-18
- Google building new robotics model Astra with 1M-token context, config leaks — lyraxana · 2026-11-18
- Leak: Google to unveil 'krypton' tomorrow, claimed to beat Fable 5.2 and GPT Astra 6.2 at lower cost — imjustnewatai · 2026-11-18
- LlamaIndex open-sources ParseBench-2 leaderboard ranking 20+ open-weight OCR models — llama_index · 2026-11-18
- GPT-6.2 Astra tops robot-code test: 2.5B net solving 79% of LIBERO, Python code hits 96.8% — burny_tech · 2026-11-18