shant_extry

Learning how to use documentation for/with AI has been the story of my last year+. I don't have the technical background you do but I've worked in product and project management, so I was never deep in code the way you've been.

I think the journey of figuring out how to actually create with AI has been as interesting as what I'm able to create. I wish I had documented more of my lessons-learned the way you have. The biggest challenge I've found is that, as you mentioned, AI often thinks more equals better. So I had to learn when "comprehensive" meant subtracting over adding. Of course, there was also the practical reason, that more documentation meant more tokens used up - more context consumed - for a given task.

As far as files and rules, since I like seeing things visually structured, I've had luck creating temporary html files that visually capture the structure (files and rules) of a given effort. I use that as my visual map and it's what I have Claude use for its own understanding. It reduces the need for reading entire docs but it also forces me and the AI to stay structured. I also mirror this in that (as of late) I use Cowork for the planning (i.e. the maintenance of that visual mapping) and Claude Code (in a completely separate instance) to run the task(s) and, in the end, pass the lessons-learned over to Cowork manually. Otherwise if they were one "mind" e.g. when I would use Claude Code to coordinate AND code, it would always add more information to its memory and it would get out of hand very quickly. Ultimately, the key for me was understanding how AI uses structure. For example, when I started using Linear a couple of months ago - prior to which I had no "formal" project management system, all of the tags and labels and 'projects' (as Linear uses the term) really helped manage efficiency in productivity. I use Linear's MCP to connect to Cowork directly and always start sessions with reading 'project' titles, labels, priorities, etc. before diving into details for a given effort.

I think this presents an opportunity to explore balance in the type of information you want and the time it takes to consume it.

I'll use podcasts as an example. I think podcasts became very popular because the host could sit with a guest for a long time and discuss important topics at depth. The problem, in my view, is that that medium locked itself into longer lengths of time that it always has to fill. I may want to hear a politician talk for 3 hours if they're running for office but I don't necessarily want to hear an actor's thoughts on life for that long (for the fifth time). Sometimes, a late night show's 5 minutes is sufficient for the latter.

Does every Substack have to include an SEO-esque preamble before it gets to the ultimate point it's trying to make or perspective it's trying to explore? I think, in an ideal situation, the format (including length) of the article/book/etc. would match the reader's capacity and willingness to read it.

One last note - just because I read it somewhere and it stuck with me - "Learning is an intelligent person's favorite form of procrastination." So if you're consuming whatever you're consuming and you feel like it's not just social media-like consumption in a different form, then more power to you.

Over the last ~2 years I cultivated a small list of newsletters. First I'd just find several regarding a particular niche and sign up to them - auto-sorting into a particular email folder for each topic. Then I'd filter them by seeing how many seem too generic (i.e. not at the level of depth I'm interested in, or by their format (content within the newsletter or linking out of it - though both are useful), and so on. Now I receive ~9 per day M-F with little repetition between them and I find it more than sufficient.

I really love this idea. I also miss the days when you could find a forum for something you were interested in and that forum became a real community. It was self-moderating, supportive, and - once people got to know each other's personalities - entertaining and funny. I'll definitely check out your site. Best of luck.

I think the "randos and AI" is a significant part of the problem. Despite finding what you want (just speaking personally) I like the idea of supporting a creator and knowing that that creator is genuinely interested in the content they're producing. Not to put down someone who is trying to make some money out of it, but a creator who focuses too much on following trends might lose the "micro-niches" that some part of their audience might be interested in following them through.

I didn't think there was much on/about the internet and devices that I was ignorant on but I literally never thought about it like this..."It's a literal felony if you were to hand a kid a porno, gore/death videos, etc, but handing a kid a phone with unrestricted internet is completely fine for > 50% of parents [1]. And, the children of these failed parents go around the schools showing other children "shock" videos to get their reactions, like (an example I know) another child being murdered, on a gore website."