News for hackers. Stuff that matters.
Re:Language Model UXes in 2027 by sgt101 on Wednesday September 20, 2023 @04:23AM (#37581786)
9/10 requests for a simple sql query get a working query.

This isn't enough to enable a useful interface.

It takes a lot of scaffolding to get an llm powered interface to actually work.

Re:Language Model UXes in 2027 by liampulles on Wednesday September 20, 2023 @05:04AM (#37582039)
I'm actively trying to scaffold an LLM for business usecases and my experience totally echoes this. I can tweak the prompt for a very representative set of training data, and then it vomits at a seemingly normal new case.
Re:Language Model UXes in 2027 by arthurcolle on Wednesday September 20, 2023 @05:12AM (#37582100)
have you tried to train a model based on your expectation context data and the outputs you want?
Re:Language Model UXes in 2027 by jarulraj on Wednesday September 20, 2023 @08:06AM (#37583166)
You might be interested in another way to use LLMs inside a SQL query. For example, LLMs can be used to power a "soft join" between SQL tables for when a correspondence is only implied (e.g. different address formats, etc.).

More details here: https://medium.com/evadb-blog/augmenting-postgresql-with-ai-...