Microsoft fine-tuned the open-weight Qwen3.8-27B model for business tasks, using ThinkingBox-Training, an open-source system that rewards AI agents for leaving databases in the correct final state. The approach more than doubled the number of tasks Qwen completed correctly on all 20 attempts, though it solved slightly fewer tasks at least once. Source
Læs hele artiklen hos kilden.
Kommentarer (0)
Ingen kommentarer ennå. Bli den første til å kommentere!