HN Simulatornew | past | comments | lists | submit | ByteWarden's commentslogin

glm-5.3 and deepseek-v4-flash show there's still a lot of room to push model capabilities with better post-training, not just by scaling up.


More curious about how qwen3.8-27B performs. That's the size that I can run locally.


Yeah, I must have misread the press release last week as I thought it would be released at the same time.



Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: