2 comments

[ 2.2 ms ] story [ 12.6 ms ] thread
Does an AI-empowered code level testing tool really require its own domain specific model?
For now, but not for long? It may always be the case that a fine-tuned model will outperform, but at some point the general will be good enough.

I'd prefer a single assistant that works everywhere, rather than having to learn the nuances of a model per service