How much of a difference is there in the answers from a base gpt3 / davinci model vs a finetuned model? (I'm assuming this finetuning isn't just the addition of a few examples in the prompt)
Aybody actually use this? My boy Beats was all up in it but he said that it didn't work on Sybase.
LFP
What's the difference between dbsensei and ThoughtSpot/Tableau Ask Data/...
there's also veezoo.ai (shameless self-promotion :))