X · @teortaxesTex
· X / Twitter
My standards for V4-Pro-Official are: match GLM 5.2 on net. I'll accept something like slightly worse DeepSWE for slightly better CritPT/FrontierMath,…
My standards for V4-Pro-Official are: match GLM 5.2 on net. I'll accept something like slightly worse DeepSWE for slightly better CritPT/FrontierMath, on merit of their later pivot to agents. If they do this, unit economics decide the rest.if they don't, well. Drinking timeTeortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞): In sum,