In practice prompt engineering and few-shot prompting with modern LLMs, due to their strong-and-only-getting-better-over-time prompt adherence, tends to be more pragmatic.
When it’s more feasible to do inference on the client (browser or desktop) I can see SLMs popping up more common in production.
It's not actually that expensive and hard. For narrow usecases, you can produce 4-bit quantized fine-tunes that perform as well as the full model. Hosting the 4-bit quantized version can be done on relatively low cost. You can use A40 or RTX 3090 on Runpod for ~$300/month.
If you want to scale up and down on demand, you can just fine tune on openai and google cloud as well.
I don't think that's true.
I can fine tune a model by renting a few A100s for a few hours, total cost in the double digit dollars. It's a one-time cost.
Running inference with the resulting model for a production application could cost single digit dollars per hour, which adds up to hundreds or even thousands of dollars a month on an ongoing basis.
That may or may not be true for use-cases that require asynchronous, bulk inference _and_ require some task-specific post-training.
FWIW, my approach towards tasks like the above is to
1. start with using an off-the-shelf LM API until
2. one figures out (using evals that capture product intent) what the failure modes are (there always are some) and then
3. post-train against those (using the evals)