News for hackers. Stuff that matters.
Re:A Competitor Crippled a $23.5M Bootcamp by Becoming a Red... by trilogic on Thursday October 09, 2025 @04:40AM (#45525082)
Nonsense, there is a big difference of tokens generated in the output. I know my stuff, and I can recognize Deepseek reasoning and Qwen thinking. Also I explained how agentic is working in the models making it very different. The quantization is irrelevant to tokens generated and agentic behavior in a model. Say what you want, you or anyone else can´t change the facts.

There are no comments on this comment yet.