I do classification with SLMs and for my tasks when I have a few thousand samples the frontier models in zero-shot and few-shot modes are embarassingly bad in comparison.
PaulHoule
I think we're past that point; they're absolutely useful already for a lot of tasks. I think it's about costs, convenience, and benefits of a frontier model for what you're doing.
david927
Local LLMs have been useful since 2024. If you don't know this then you are just far behind. Catch up!
segmondy
until its cheaper to train and infer than 100k gpu data centers...i doubt it will ever compete.
comments (4)
PaulHoule
david927
segmondy
buffer_overlord