Absolutely agree with this, the ratio of talk to output is insane, especially when the talk is all about how much better output is. So far the only example I've seen is Claude Code which is mired in its own technical problems and is literally built by an AI company.
> Write your own code without assistance on whatever interval makes sense to you, otherwise you'll atrophy those muscles
This is the one thing that concerns me, for the same reason as "AI writes the code, humans review it" does. The fact of the matter is, most people will get lazy and complacent pretty quickly, and the depth of which they review the code/ the frequency they "go it alone" will get less and less until eventually it just stops happening. We all (most of us anyway) do it, its just part of being human, for the same reason that thousands of people start going to the gym in January and stop by March.
Arguably, AI coding was at its best when it was pretty bad, because you HAD to review it frequently and there were immediate incentives to just take the keyboard and do it yourself sometimes. Now, we still have some serious faults, they're just not as immediate, which will lead to complacency for a lot of people.
Maybe one day AI will be able to reliably write the 100% of the code without review. The worry is that we stop paying attention first, which all in all looks quite likely
Those of us building are having so much fun we aren't slowing down to write think pieces.
I don't mean this flippantly. I'm a blogger. I love writing! But since a brief post on December 22 I haven't blogged because I have been too busy implementing incredible amounts of software with AI.
Since you'll want receipts, here they are:
- https://git.sr.ht/~kerrick/ratatui_ruby/tree/trunk/item/READ...
- https://git.sr.ht/~kerrick/rooibos/tree/trunk/item/README.rd...
- https://git.sr.ht/~kerrick/tokra/tree
Between Christmas and New Year's Day I was on vacation, so I had plenty of time. Since then, it's only been nights & weekends (and some early mornings and lunch breaks).
I believe they'll be maintainable long-term, as they've got extensive tests and documentation, and I built a theory of the program [2] on the Ruby side of it as I reviewed and guided the agent's work.
I am getting feedback from users, the largest of which drove the creation of (and iteration upon) Rooibos. As a rendering library, RatatuiRuby doesn't do much to guide the design or architecture of an application. Rooibos is an MVU/TEA framework [3] to do exactly that.
Tokra is basically a tech demo at this stage, [4] so (hopefully) no users yet.
[0]: https://ruby.social/@[email protected]/1159351822843...
[1]: https://ruby.social/@getajobmike/115940044592981164
[2]: https://www.sciencedirect.com/science/article/abs/pii/016560...
Let me fix that for you:
No more AI thought pieces until you SHOW us what you build!
And I think it can safely be generalised to:
No more thought pieces until you show us what you build!
And that goes double for posts on LinkedIn.
I’d say it’s rarer to find a dev who doesn’t use AI tools in their arsenal these days, that’s why your question sounds so odd to me.
Those not shipping are talking about it.
Absence of evidence, while not the only signal, is a huge fucking signal.
That wasn't supposed to be an opportunity for you to get defensive, but an opportunity for you to show off awesome projects.
I'd go so far as to say that for the vast majority of people, if you don't know what you're going to say when you sit down to write, THAT is your problem. Writing is not thinking, thinking is thinking, and you didn't think. If you're trying to think when you should be writing, that's a process failure. If you're not Stephen King or Dean Koontz, trying to be a pantser with your writing is a huge mistake.
What AI is amazing for is taking a core idea/thesis you provide it, and asking you a ton of questions to extract your knowledge/intent, then crystallizing that into an outline/rough draft.
You're free to adopt this cynical and pessimistic outlook if you like but you're going a bit far trying to force it on others. Gawd.
If your argument starts with "how do you know you're not the best in the world unless you try" you fucked up.
The physical (and genetic) demands of athletics aside, we were talking about writing. Just starting on a lark is what worked for Haruki Murakami. Again, it's very unlikely you'll be the next Murakami. But at least you'll improve a lot at something you find interesting! What is the downside here, exactly? Unless you're an opportunity-cost-minimising, industrial-output-maximising kind of person. That's fine, but that's not everyone.
The same pattern holds at the elite levels of most things.
How does it hold for writing?
If you don't have that wisdom, trying to pants something is going to result in writing yourself in circles, contradictions, inconsistencies, incoherence of idea, etc.
We build a personal finance tool (referenced in the article). It's a web/mobile/backend stack (mostly React and Python). That said, I think a lot of the principles are generalizable.
> Writing _is_ the thinking. It's a critical input in developing good taste.
Agree, but I'll add that _good_ prompt-writing actually requires a lot of thought (which is what makes it so easy to write bad prompts, which are much more likely to produce slop).
AI is a general-purpose tool, but that doesn't mean best-practices and wisdom are generalizable. Web dev is different than compilers which is different than embedded and all the differences of opinion in the comments never explain who does what.
That said, I would take this up a notch:
> If you ask AI to write a document for you, you might get 80% of the deep quality you’d get if you wrote it yourself for 5% of the effort. But, now you’ve also only done 5% of the thinking.
Writing _is_ the thinking. It's a critical input in developing good taste. I think we all ought to consider a maintenance dose. Write your own code without assistance on whatever interval makes sense to you, otherwise you'll atrophy those muscles. Best-practices are a moving train, not something that you learned once and you're done.