7/20/26
Very good read. This lines up with a lot of my feelings on AI usage right now. Some notes I wrote while reading.
This part is very interesting:
Even if such systems continue to work, I find two things: 1) that now advocates for this state of affairs have pivoted into acknowledging that this is the end state of their systems and 2) they seem to be accepting it as the way forward.
This has really been my core sticking point (from a being asked to do this by my employer perspective) with adopting it as a way to write code… Is this going to be totally fucked in a year???
The shift from “agentic engineering” to actually we should just be “vibe coding” is wild. I’ve been seeing that too, I think. (still reading)
WOW haha, I feel so SEEN hahaha:
It’s simple. Generation is not the slow part of coding. Theory-building and review are. And plausible-enough things are extremely hard to debug and understand. But the machines are so fast at producing things. If you are going to review their work, you aren’t really taking advantage of their most powerful property, which is speed. But theory-building and review are also the programmer’s most important role.
I love any article that leaves me with 4 more open tabs of interesting sounding links too
I am very much feeling the bobsled right now. I’m curious where my coworkers fall on this journey. I’m at the still reading “all” the code stage and haven’t switched over to full generation yet. But I’ve been at all of those stages described thus far too.
At work at any rate, I get the itch to use it on personal projects sometimes when I feel impatient or low on motivation to push through a problem. I’m avoiding setting it up in any personal IDEs or finding a plan to pay for or whatever at home.