Comment by simonw
19 hours ago
I certainly hope that's not true, given that I've dedicated 7+ years to my main open source projects at this point.
I take some reassurance from knowing that they are indeed used by real people to solve real problems though.
Now what percentage of the 200$ have been used on the useful stuff and how much on exploration or other stuff.
How long would it taken you to do it yourself? How much longer will the next task take you, compared to when you would’ve written the code yourself. How is the mental model compared to when you would’ve written it yourself?.
I’m not saying you’re wrong, again there are use cases. But the calculation is not plain and simple it goes deep into our perception, perceived productivity versus actual productivity.
I’ve 2 months maxxed out all 6k of Claude Code and bought Antigravity on top. My codebase became 140k lines. I introduced tons of bugs and spent another 2 months, deleting 80k of code. I wish I would’ve just chatted with AI and not let agents touch my codebase. I would’ve saved approx 300$ subscription prices a month and 2 months of my life.
I had that experience back in January! I used it for a joke in a talk recently... did anyone really need a half-finished buggy slow implementation of a JavaScript interpreter in Python? They did not. https://github.com/simonw/micro-javascript
It's taken me the best part of this year to readjust and find a pace and level of ambition that fits.
It was challenging for me as well, but my pace and level is now that I use it for these cases at the moment:
New language, infrastructure, general level of understanding of something I barely have an idea of.
Rubber duck debugging, if i dont know the correct solution
Checking my code for issues and bugs.
But not for:
- writing my code - agentic coding (help me)
The inference has reduced drastically. It’s basically just chatting. I don’t let it write anything, but sometimes I purposely use the browser window instead of them sitting in my codebase, because I know it gets things subtly wrong and migth focus on the wrong things.
The same way people used to say don’t copypaste code at least write it out I think it’s still true. It helps to buidl the mental model and to find the right abstractions.