why would you waste your time messing around with a team of expensive ml engineers and data scientists that produce vastly inferior to a llm.
We ripped out custom homegrown ml models that were developed in last 10 yrs and put an llm in its place. Its the opposite of wasteful. Even local gemma models are vastly superior.
There’s a middle option. Once you figure that out, you’d soon understand my point today or tomorrow. I’ve been in this field for 21 years and I use LLMs everyday. I also know when to not use them.
It's the transportation "mode shifting" difficulty. Per the AI, the term of art is "Pure Transfer Penalty". It's the "ick" when doing bike => bus => bike instead of "only bike" or "only car".
Mode switching has a cost. Usually std::sort is good enough compared to picking the prime optimal algorithm for your expected shape. Just call the function and get on with your day.
I think both your arguments are true. It all depends on the velocity of the capability growth and the fact that opportunity cost is expensive.
Once we get out of this hypergriwth phase the very same AI companies that now are giving you llms will provide a service that employed a rich mixture of optimized models that will reduce the operational costs to achieve the required results
I'm a little confused: LLMs were invented in 2018.
Is the middle option asking LLM to generate a classic ML model? Or generate tons of them and pick the best?