I'm no expert and I'm biased because of my current work but fine-tuning (especially LoRA) is one of the most powerful and reliable ways to get LLMs to fit your custom needs.
Better than prompt engineering and even embeddings.

That's all I can say.

The open web is dead, long live the open web. ⌐◨-◨

Building /warpcast and /farcaster

— gabrielayuso.com

My pipeline has been:
- test wild prompts on largest (340B+) model I can find
- find best outputs and test on 24Bs
- generate 100+ examples and see if I can get it tuned on something much smaller
And yes, LoRA has proven to be incredible for a lot of my use cases

"Creative Technology" 🤌🏽

@ google creative lab

Owner of /makerspace - come build with us!