In this episode, Dipendra Kumar, Staff Research Scientist, and Alnur Ali, Staff Software Engineer at Databricks, discuss the challenges of applying AI in enterprise environments and the tools being developed to bridge the gap between research and real-world deployment.
Dipendra on model strategy:
“And so what we have found useful is that you can train like smaller LLMs, which are first of all, more cost effective. And on the specific task, and get them to be much more accurate than these general purpose models.”
Alnur on real-world complexity:
“There's a few things going on here. One is we're assuming these test cases are all kind of similar. Two is we're assuming there's no interrelationship or serial dependencies between these test cases. Like, sorry, that actually just, neither of those are true in practice, right? The data that you kind of tune your model on, be it an LLM or something else offline, it's never going to be what you see online.”
