Developers call Sol 6.1 slow and lazy despite DevDay hype
kimmonismus · x · 2026-10-04
Adding to post-DevDay disappointment, kimmonismus reports that OpenAI's Sol 6.1 is slow in real use — especially versus Opus 5.5 — and feels "lazy," requiring prompting to take action like the old Opus 5, while Astra feels more eager. Quoted user scottstts is blunter: OpenAI hyped "20 new things" before DevDay but nothing mattered; Sol 6.1's benchmark performance and efficiency exist only on paper, and TPS-normalized usage remains severely broken compared to Claude.
More from Models
- Developers praise Gemini 4 Neon: not the smartest model, but the best to work with — soumitrashukla9 · 2026-11-20
- QuixiInfer: from-scratch Rust engine runs DeepSeek with 256k context on a single RTX 5090 at ~30 tok/s — QuixiAI · 2026-11-20
- Matthew Green questions why a compromised inference provider served an abliterated model — matthew_d_green · 2026-11-20
- GPT 6.2 Sol remains #1 for computer/browser use, says Matthew Berman — MatthewBerman · 2026-11-20
- Microsoft's MAI models have been front-page on Hacker News since Ignite debut — marlene_zw · 2026-11-20
- Gemini 4 Carbon tops graduate-level physics benchmark but loses on agentic tasks — ArtificialAnlys · 2026-11-20