It gets very similar performance, so maybe it is possible. But also when I fine-...

		phillipcarter on Dec 13, 2023 \| parent \| context \| favorite \| on: A new old kind of R&D lab It gets very similar performance, so maybe it is possible. But also when I fine-tune 3.5, its response quality is indistinguishable from when I use the base model. All of this is to say: this shit is way harder than it needs to be. I'm not an ML engineer but I do know my data and how to get it. Why is it still so hard to specialize a model?

Because we don’t have a clear understanding of how the things work yet.