antirez(@antirez):Still didn't attempt any quality testing, but let's say that GPT 5.6 Sol was able almost unassisted to write this Laguna S2.1 inference implementation following the other two models in DwarfStar, and it is very fast, 50 t/s generation, very fast prefill as well.

antirez

@antirez

Reproducible bugs are candies. I like programming too much for not liking automatic programming.

加入 May 2007

797 正在关注 77.5K 粉丝

antirez@antirez

2026.07.22 22:32

Still didn't attempt any quality testing, but let's say that GPT 5.6 Sol was able almost unassisted to write this Laguna S2.1 inference implementation following the other two models in DwarfStar, and it is very fast, 50 t/s generation, very fast prefill as well.

显示更多