A “soft join” between SQL tables for when a correspondence is only implied

A “soft join” between SQL tables for when a correspondence is only implied(twitter.com)

3 points by crazy_marksman 2 years ago | 4 comments

woshiwan 2 years ago |

Not super relevant. What are some common ways in database to join tables with no common column?

I don't believe there is a solution otherwise. All you can do is cross join.

aka no join key exists, so ask a language model to hallucinate the next best thing.

most of these “real world applications” of language models look suitable as little more than parlor tricks, certainly not something for production.

then again, that’s why all of it is called “ai.”

crazy_marksman 2 years ago | |

I appreciate your view on using LLMs in production. However, I think the ability to use ML/AI directly within databases is a significant step forward. Most production systems already rely on predictions, so the idea of using them without leaving the database is both interesting and valuable.