> I hated writing software this way. Forget the output for a moment; the process was excruciating. Most of my time was spent reading proposed code changes and pressing the 1 key to accept the changes, which I almost always did. [...]
That's why they hated it. Approving every change is the most frustrating way of using these tools.
I genuinely think that one of the biggest differences between people who enjoy coding agents and people who hate them is whether or not they run in YOLO mode (aka dangerously-skip-permissions). YOLO mode feels like a whole different product.
I get the desire not to do that because you want to verify everything they do, but you can still do that by reviewing the code later on without the pain of step-by-step approvals.
I have come to the conclusion that many people are going to live this AI period pretty much like the five stages of grief: denial that it can work, anger at the new robber barons, bargaining that yeah it kinda works but not really well enough, catastrophic world view and depression, and finally acceptance of the new normality.
I recently spoke to a very junior developer (he's still in school) about his hobby projects.
He doesn't have our bagage. He doesn't feel the anxiety the purists feel.
He just pipes all errors right back in his task flow. He does period refactoring. He tests everything and also refactors the tests. He does automated penetration testing.
There are great tools for everything he does and they are improving at breakneck speeds.
He creates stuff that is levels above what I ever made and I spent years building it.
These takes are growing increasingly tiresome, I have to admit. They are pretty much all just tacit admissions of some kind of skill issue with this new class of tool, but presented with a sheen of moral outrage. I don’t think anyone’s buying it anymore. Figure it out.
> I have no reason to expect this technology can succeed at the same level in law, medicine, or any other highly human, highly subjective occupation.
I mean, if anything, I would expect it to help bring structure to medicine, which is an often sloppy profession killing somewhere between tens of thousands and hundreds of thousands of people a year through mistakes and out of date practices.
As medicine is currently very subjective. As a scientific field in the realm of physical sciences, it shouldn't be.
They really shouldnt have read all the changes individually. What you gotta do is set up your VC properly so these changes are seperated from good code, and then review the whole set of changes in an IDE that highlights them, like a proto PR. Thats far far less taxing since you get the whole picture
The author has arrived at resentful acceptance of the models power(eg: "negative externalities", "condemn those who choose").
But the next step for many is championing acceptance. Eg "that the same kind of success is available outside the world of highly structured language" .. it actually is visible when you engage with people. I'm myself going through this transition.
giving partial credit to Rust, the language, for shipping production code because you "hate" the experience of agent-driven development so much is an amazing move. i didn't think we could push things forward so fast. i guess Rust is just that powerful
The door is really opening for programmers who like getting stuff made, and really closing for those who like making stuff at a low level.
No need to get out the chisel to carve those intricate designs in your chair back. We can just get that made by pressing "1". Sorry, those of you who took pride in chiseling.
I'm definitely in the latter group. I can and do use AI to build things, but it's pretty dull for me.
I've spent hours and hours putting together a TUI window system by hand recently (on my own time) that Claude could have made in minutes. I rewrote it a number of times, learning new things each time. There's a dual goal there: learn things and make a thing.
Times change, certainly. Glad to be in semi-retirement where I still get to hand carve software.
15 comments
[ 1.7 ms ] story [ 47.8 ms ] threadThat's why they hated it. Approving every change is the most frustrating way of using these tools.
I genuinely think that one of the biggest differences between people who enjoy coding agents and people who hate them is whether or not they run in YOLO mode (aka dangerously-skip-permissions). YOLO mode feels like a whole different product.
I get the desire not to do that because you want to verify everything they do, but you can still do that by reviewing the code later on without the pain of step-by-step approvals.
This again showed me that I can't go in YOLO mode. Things like this are disastrous if left to fester in a codebase.
I'm still at the bargaining phase, personally.
He doesn't have our bagage. He doesn't feel the anxiety the purists feel.
He just pipes all errors right back in his task flow. He does period refactoring. He tests everything and also refactors the tests. He does automated penetration testing.
There are great tools for everything he does and they are improving at breakneck speeds.
He creates stuff that is levels above what I ever made and I spent years building it.
I accepted months ago: adapt or die.
I mean, if anything, I would expect it to help bring structure to medicine, which is an often sloppy profession killing somewhere between tens of thousands and hundreds of thousands of people a year through mistakes and out of date practices.
As medicine is currently very subjective. As a scientific field in the realm of physical sciences, it shouldn't be.
But the next step for many is championing acceptance. Eg "that the same kind of success is available outside the world of highly structured language" .. it actually is visible when you engage with people. I'm myself going through this transition.
No need to get out the chisel to carve those intricate designs in your chair back. We can just get that made by pressing "1". Sorry, those of you who took pride in chiseling.
I'm definitely in the latter group. I can and do use AI to build things, but it's pretty dull for me.
I've spent hours and hours putting together a TUI window system by hand recently (on my own time) that Claude could have made in minutes. I rewrote it a number of times, learning new things each time. There's a dual goal there: learn things and make a thing.
Times change, certainly. Glad to be in semi-retirement where I still get to hand carve software.