[trollbridge]

I’m finding the same usage of LLMs in terms of what actually I use them for day to day. When I need to look up arcane information, an LLM generally does better than a Google search.

[bluefirebrand]

How do you verify the accuracy of "arcane information" produced by an LLM?

"Arcane Information" is absolutely the worst possible use case I can imagine for LLMs right now. You might as well ask an intern to just make something up

[trollbridge]

I check the sources. Usually this is documentation for some package I’ve never used before.

I will also admit to using LLMs to create unit tests, and then building a test suite to test this unit tests.