LLMs still completely won't admit that they're wrong, don't have enough information or that the information could have changed - Asking anything about Svelte 5 is an incredible experience currently.

At the end of the day it's a tool currently, with surface-level information it's incredibly helpful in my opinion - Getting an overview of a subject or even coding smaller functions.

What's interesting in my opinion is "agents" though... not in the current "let's slap an LLM into some workflow", but as a concept that is at least an order of magnitude away from what is possible today.