Aggressively red-teaming your own work with LLMs is a good habit to get into. Prompts like “I’ve been told me to find the flaws in this argument/presentation/code file/etc.”. Doesn’t save any time, but is pretty educational, as long as you go back and forth a lot. It can fall into a style disagreement loop between two equivalent code blocks as it will try to find something wrong if instructed to do so, which is interesting.

If you don’t do this constantly, LLMS can certainly lead you right down the Dunning-Kruger path (though that’s a big oversimplification of a whole collection of psychological features from idee fixe to narcissism to fear of failure/criticism). If you really work at getting the LLM into the proper state it will happily rip your work apart in a rather cruel and indifferent manner, like an unsympathetic corporate gatekeeper who relishes exposing your flaws in a public setting. Debate club is another tactic that’s a bit less harsh, you have the LLM flip back and forth between defense and prosecution of your work.

I think this should be the default setting, but it doesn’t encourage engagement, the average customer will think the LLM is a mean jerk if it starts off like that.