Yeah this is how I interpret it. Type text into the chatbot, copy and paste the outputted code. If it fails to compile, paste the error message and get the resulting code. Similar if it fails at runtime. Supply the LLM with additional code files where necessary but don't really look at the code, just copy and paste in, copy and paste out.
Copy paste? Use something like desktop commander and just let it edit the files for you directly. It'll even run commands to test it out. Or go further and use Cline/RooCode and if you're building a webapp it'll load your page in a small browser, screenshot the contents, and send that to the model. The copy-paste stuff is beginner mode.
When I've been experimenting with Cursor I've found that one of the essential parts is the agent MUST be able to close the loop itself for it to be useful in any real sense.
So if you are having the agent write a script to call an endpoint and do something with the result. Have it write a script that does that and then ask it to run the script itself. It will then be able to close the loop by itself and iterate on the code until it does what you want (usually).
It is also very useful to ask the agent to write a test for something and then run that test to close the loop in the same way.
The vibes are much better if you just tell it to run a certain command, then it can see the error message and you don't have to paste back and forth so much. You can go make a cup of tea and it'll just iterate on changing files and running that command until it does the desired thing.
This is what AI-oriented IDEs like Cursor streamline - the LM gets immediate feedback from things like code completion, linter, build errors, test failures etc, and can immediately iterate without you having to do anything about it (sometimes overly aggressively even tbh).
Copy paste is so last year, just turn on agent mode in VS code or Cursor. It took me only a single prompt to convert a set of messy razor pages into a nicely structured React application.
How else are people using LLMs to code? Other than this?
Its so fast to do these things. Seems dumb not to use an LLM to interpret an error message if you don’t immediately know the problem. And if it doesn’t work you can alway abort and do it yourself. The whole code gen and debugging process might take 45 seconds.
Sure its dumb if you’re writing some short simple function. And you need to be in the loop and understand all the changes you are making in a professional setting. But that just sounds like the basic workflow of coding with an LLM.
