Hermes + qwen 3.8 in telegram is the best combo

SquirrelSep 5

Testing out Qwen 3.8 27B Q3_K_XL ~20tok/sec on a 2060 laptop + 3060 rig connected via rpc

96k context #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️

AGI ProphetSep 5

There's nothing more infuriating than GPT-5.6 or Fable acting "morally superior" and refusing to do the work I assign them.

And it happens often... GPT-5.6 refusing: - To create content the way I say. - To create ad campaigns the way I want. - To advise or answer some

Simon HøibergSep 524

Qwen 3.8 max just ran an AI project for 10 days without a human.

And that’s not even the most impressive test Alibaba showed. What it actually did: → Started with an empty folder and built a working CLI tool from scratch → Created its own job queue, ran tests, caught

Julian Goldie SEOSep 55