- You can use AI to look through docs and do research.
- You can use AI to structure your argument.
- You can NOT use AI to actually write the prose.
- You can use AI to proofread, especially for how effectively you've communicated.
I don't know, man, that sounds a lot like using AI to write. Your writing probably says "load-bearing" less than Claude's outputs, but I'm not sure it's much less AI.
Structuring arguments: bad idea. Here you're having the model do your thinking for you. The problems that occur with having it write text recur at a macro level; too-obvious patterns. Readers just want to know what the prompt was.
Writing the prose: obviously not.
Proofreading: I think this works pretty great, as long as you have a structure to how you're doing it. "How do I make this better or sharper": bad, you're having the model structure your arguments for you. But for a predefined rubric of stylistic things --- writing you know how to do, that's just tedious to check manually? Hard to see a downside.
This reminds me a lot of smokers who all have a great strategy beat the nicotine addiction. Only smoke on the weekends when out partying with friends, only smoke to use the extra sense of energy, only smoke to suppress my appetite, go to the gym 5 hours a week to offset the negative health impacts of smoking etc. etc.
In reality most smokers will converge to about a pack a day.
Never, never, do that!
I draft all my own text that anyone will ever read as “that’s James Bach talking to me.” I want no one to be able to credibly question that.
But of course, writing is more than merely drafting the text. As I draft, I write about ideas that other people or AI may have helped me come to.
- Brainstorming with AI is fine, but it takes skill to use it as food for thought, rather than as a source of answers.
- Do NOT structure your blog post with AI. Once the structure is there, it is almost impossible to humanize it.
- Do NOT use it for writing a draft. Same as above. A few times I did it, and ended up rewriting from scratch. Unsloppification is hard.
- AI for proofreading is wonderful. But I always prompt with "only fix grammar mistakes, do not change the style" and actually look at all changes. If not kept in check, it too eagerly homogenizes style.
Of course, this is different than having the argument ready and using an AI to make it read a little better, which at that point, is just details.
Honest question - where does an Author like the above place in your authenticity framework?
slop has been around a lot longer than ai - the contingent needs to realize what it is they hate. instead of "don't use ai to write" it's "don't use ai to write slop" or better: "don't write slop"
However, I don't think it's a good idea to replace our own thinking with an AI, and that's what I'm trying to avoid with the way of working proposed in the article.