logoalt Hacker News

perching_aix • yesterday at 11:32 PM • 1 reply • view on HN

I still have no idea why this is useful. Models are atrocious without reasoning, for classification and otherwise, and this doesn't even just eschew reasoning afaik, but parts of the models as well for lower latency and cost. I genuinely do not see the point.

What differentiates this from training a classifier model? That it comes pretrained with general knowledge?


Replies

foopod • today at 1:45 AM

I think that is exactly the value prop, you don't need to train a classifier. You get something that works well enough to validate your product/feature/whatever before investing in training.