News for hackers. Stuff that matters.
Re:Five Qwen3.8-27B models outperform Fable 5 Using GVS5H Ha... by hirako2000 on Sunday October 25, 2026 @01:57AM (#50228740)
Also why not comparing harnessed Qwen to harnessed other LLMs.
Re:Five Qwen3.8-27B models outperform Fable 5 Using GVS5H Ha... by chvid on Sunday October 25, 2026 @04:31AM (#50229438)
I guess one point is you can run Qwen on a local machine.

It is not public knowledge how Fable 5 works - it is all hidden away behind a web service - for what it is worth it might a hybrid architecture with harness, loops, tools etc. combined with a traditional llm like what is done here.

Re:Five Qwen3.8-27B models outperform Fable 5 Using GVS5H Ha... by hirako2000 on Sunday October 25, 2026 @10:26AM (#50231943)
Fair points. But harness at this point makes more difference than using the best model.