“If you have exact questions, you need to be able to provide exact answers,” Krishnamurthy told us. “But I think inexact questions are what people are also going to expect. When you think about agentic workloads and operational databases, you want to be able to ask more flexible questions.” An example might be a natural language query that takes into account context, such as previous interactions.
Krishnamurthy described “AI native infrastructure,” including vector indexing, text indexing, and graph technology where “you combine structured and unstructured data, you have to be operating in terms of inexact results and data quality.”
That description sounds like someone who describes what ai can do with a db, rather than trying to describe a real use case and then finding the tool for the job
Google can’t even autocorrect words in search queries anymore
And is it just me, or has Google Maps’s navigation gotten way worse recently as well? I was using it a couple days ago and twice it had me literally going in circles.
Everything sucks more as soon as they use llms. And they keep going.
Great, so when I query the database
SELECT password_hash FROM users WHERE username IS "OwOArchist"it will return 5 different hashes from people with vaguely similar usernames … and none of them the actual one I needed in order to verify my password and log in.For fuck’s sake, Google – database queries need to be deterministic!
What!? Don’t you like AI, we are shoving down everyone’s throats, because we overlevereged into a shitty technology, without actually figuring out it’s consequences?