What is going on right now?

I won't say too much, but I recently had an experience where it was clear that when talking with a colleague, I was getting back chat GPT output. I felt sick, like this just isn't how it should be. I'd rather have been ignored.

It didn't help that the LLM was confidently incorrect.

The smallest things can throw off an LLM, such as a difference in naming between configuration and implementation.

In the human world, you can with legacy stuff get in a situation where "everyone knows" that the foo setting is actually the setting for Frob, but with an LLM it'll happily try to configure Frob or worse, try to implement Foo from scratch.

I'd always rather deal with bad human code than bad LLM code, because you can get into the mind of the person who wrote the bad human code. You can try to understand their misunderstanding. You can reason their faulty reasoning.

With bad LLM code, you're dealing with a soul-crushing machine that cannot (yet) and will not (yet) learn from its mistakes, because it does not believe it makes mistakes ( no matter how apologetic it gets ).

>"It didn't help that the LLM was confidently incorrect."

Has anyone else ever dealt with a somewhat charismatic know-it-all who knows just enough to give authoritative answers? LLM output often reminds me of such people.

I'm pretty sure I'm that guy on some topics.

>"I'm pretty sure I'm that guy on some topics."

The use of 'pretty sure' disqualifies you. I appreciate your humility.

I don't know, man. I really don't know. I can't tell whether I'm really good at making inferences from tidbits of information, or really good at speaking confidently.