Ive used chatGPT to help me learn new stuff about which I know nothing (this is it's best use imo) and also write boilerplatey functions, eg. write a function that does precisely X.
Having it integrated into my IDE sounds like a nightmare though. Even the "intellisense" stuff in visual studio is annoying af and I have to turn it off to stop it auto-wrecking my code (eg. adding tonnes of pointless using statement). I dont know how the integrated llm would actually work, but I defo dont want that.
> "An LLM agent runs tools in a loop to achieve a goal."
This is the magic sauce compared to copy-pasting snippets to a web browser.
It can automatically read code, search through it and modify multiple files automatically. Then it can compile it, run tests, run the actual application to check it works etc.
Eventually you start to anticipate what it will output and you can get ahead of it tabbing through tons of code that you were intending to write.
But when it doesn’t output what you want you spend mental energy and extra time reorienting to get back on track.
About 50% of the time it works every time.
Writing the mindless boilerplate is when I'm thinking about the next step. If I didn't write it, i'd still have to take the time to think things through for the next step.