galenmarchetti

what are these "nasty surprises"? they're really not that different

then why hasn't the central bank done this yet

that's a fair point. we use "ontology" throughout the product because of the influence from Palantir, and the fact that the structure we use in the product (from palantir) is in fact a bit different from what most people would create in semantic layers like dbt or cube

but i agree it's confusing. we are considering changing the naming around to account for this. i appreciate the feedback!

thank you! that's exactly where we're going with this. we're still in the early days, so let us know how you get along!

we're using OpenAI's API for business. they don't train on data sent to the business api, unlike the consumer tier

this is still an early beta, so at the moment everything is only available with OpenAI's API. however, for people who want to use it in a higher security environment, we'll support switching OpenAI with any hosted model API including on-premise or models held in private VPCs. that way people can manage their data with no exfiltration to a third party

have worked with waku in the past, love the vision

it depends on whether you want to live life with work-as-someone-paying-for-your-time or whether you want to live life as work-as-perfecting-and-delivering-on-craft

you can have an attitude towards spending the short hours you have on this earth attempting to produce quality work that others appreciate and make their lives easier in some way, as opposed to writing those hours off as sold to someone else

they kept 2 nonstop routes to NYC, 1 to Chicago, 1 to SF, but none to DC

wouldn't have guessed that. that NYC pull is huge

yeah I agree with this - good text2sql is essential but just one part of a larger stack that will actually get there. Seems possible tho

and then add in ambiguity in the business terms / intention behind the query. still a big need for something like semantic layer or ontology to sit between business and at least right now that stuff hasn’t been automated away yet (it should be though)

still need someone to build the semantic layer, why not use text2sql or something similar for that