Hardly a week goes by without a breakthrough in LLMs (large language models). They're cheaper to train and getting smarter, so why bother with their little sibling SLMs (small language models)?
For any developer team serious about delivering practical AI, it all comes down to focus and fit. LLMs are great for general, non-domain-specific tasks, but when AI needs to be truly useful in a business context, an SLM, or even a federation of SLMs supporting an LLM, is often the smarter choice.
