The problem with AI is that it's entire selling point is saving time by not needing to think very deeply about topics.

The writing is downstream of that.

steve-atx-7600 25 minutes ago | parent [-]

I think that is a problem between keyboard and chair situation. I use codex in addition to my own thinking through use cases and talking to stakeholders & domain experts to augment my understanding and find gaps in my plan. In other words, I work how I worked before but with a bunch of agents helping me research and diagram out plans faster before I start coding something.

	▲	0c3ca83 20 minutes ago \| parent [-]
		I agree, it sounds like you have a problem between your keyboard and chair, if you're generating any volume of output and not getting it in detail. The act of vetting it and finding the failures will increase understanding, but at a cost in speed over doing the research from scratch. (Generating subtly wrong text is often a good way to test understanding, and the output of AI systems is typically a mangled clone of some other well understood system. A very good exercise is building your internal pattern recognition so you can tell what's been mangled, mashed, and served up) AI is very good at making the mash sound plausible, however, so if you don't look extremely closely, you end up repeating instead of dissecting it. And if you're hoping to learn from the AI how to design a system, you're in trouble.