Hacker News Reader

Routing in agent pipelines is another use. "Does user prompt A make sense with document type A?" If yes, continue, if no, escalate. That sort of thing

View on HN

For this type of repetitive application I think it's common to "fine-tune" a model trained on your business problem to reach higher quality/reliability metrics. That might not be possible with this chip.

They say LoRA finetunes work.

Reply on news.ycombinator.com