I think it’s much more simple than that. It comes down to caring.
I’ve had a long discussion with a coworker on a long drive.
What we came to realize is the difference in our attitude towards writing code.
I approach it as craft. Even when I’m doing 100% of my coding with an agent these days. I still care about the result to be of high quality and maintainability. I still use my system design knowledge to guide the agent to produce scalable systems.
He treats it like just a job. If it’s good enough he ships. The edge cases and bugs don’t matter. Can be fixed later.
But in my mind that’s a fallacy. We all know things don’t get fixed later unless they are obvious defects and users complain.
Instead we get slow degradation of overall quality. All those small issues compound overtime to create a brittle systems that is difficult to debug and maintain.
My mental model of software engineering is like this. Each commit/PR is a small LEGO block. If you make them well they’ll snap well and create a stable structure that can withstand forces. If every LEGO block you make is just slightly off here and there. Your structure becomes unstable and will always have faults and will always have failures under unpredictable environmental pressures.
And this is why I mildly dislike the term “software engineer”. If a mechanical engineer took your colleague’s approach toward their work, they would be legally liable for engineering malpractice.
> Originally developed by the Israeli company Mirabilis in 1996, the client was bought by AOL in 1998, and then by Mail.Ru Group (now VK) in 2010.[2]
https://en.wikipedia.org/wiki/ICQ
My ICQ UIN was one of the few online accounts that I completely lost control of. Some "Russian hacker" took it over, by guessing the password, credential stuffing, or some other method, and I noticed that my profile had been usurped into a Cyrillic one. And that was long, long before 2010.
Users have the option of silent/automatic degradation or a complete halt. I have it set to stop rather than degrade because I want to know when I've hit the safeguard.
From the claude settings:
> Switch models when a message is flagged
> When safeguards flag a message, automatically switch to a different model to keep chatting. When off, your session will pause instead. Applies to web and remote sessions.
FWIW I get a ton of usage out of fable and it's only happened to me once.
I don’t know how true that is. But I read a theory somewhere that people developed bigger brains when they started eating more fish which contains omega 3s.
That’s false. Carbs are not a requirement for human body. Proof of that are native populations living far north, exclusively off of animal food sources.
Human body prefers ketones as a source of energy. But glycogen is faster.
My simplified mental model is like this. Ketones are normal gasoline. And glycogen is racing fuel (ethanol). If you run a stock car on racing fuel it may start and drive for a while but it’s damaging the engine and creates unnecessary wear.
Also not really supported by anthropology or science.
The only folks who think like this are folks who choose to believe weird dietary theories to support a pre chosen stance, like the carnivore diet or some form of excess(in the form of self-care/diet)
I’m not advocating a carnivore diet nor eat like that. Had croissants today! But it’s true that people of the north do not eat carbs as they simply do not exist there.
“Ketones are normal gasoline” is a very fringe view.
Ketone supplements have been available for a while, and nobody was able to show any benefit of using them. 100% snake oil.
If on the other hand you want to produce ketones endogenously, you basically have to put your body in a state of starvation. It’s not really gasoline then, more like burning the passenger seats as fuel so you can arrive at the destination.
Fruit were completely different and a lot less sugary and more starchy than they are today. We wouldn’t recognize most fruit neither by look nor by taste.
It's actually insanely difficult to get LLMs not to produce comments. Even with explicit "NEVER LEAVE ANY COMMENTS WHATSOEVER", they still do, across basically all providers.
No problems with GPT-5.6 Sol here. I have an agent file that says, among other things, only to document purpose and intent, not just what the code does, and not write obvious comments. It's been so effective that it often doesn't comment anything at all, including some stuff that's so niche that it must be explained carefully. As a result, I've had to pull back a bit and tell it explicitly which areas to actually add comments for.
Every single time Claude wrote a comment i replied in all caps FUCK YOU CLAUDE I TOLD YOU NEVER TO WRITE COMMENTS, WRITE IT DOWN SO YOU NEVER FORGET: YOU DO NOT WRITE COMMENTS. ONLY HUMANS WRITE COMMENTS. and after like 3 or 4 rounds of this it finally stuck and i haven't seen a Claude comment on my personal machine in months.
I’ve had a long discussion with a coworker on a long drive.
What we came to realize is the difference in our attitude towards writing code.
I approach it as craft. Even when I’m doing 100% of my coding with an agent these days. I still care about the result to be of high quality and maintainability. I still use my system design knowledge to guide the agent to produce scalable systems.
He treats it like just a job. If it’s good enough he ships. The edge cases and bugs don’t matter. Can be fixed later.
But in my mind that’s a fallacy. We all know things don’t get fixed later unless they are obvious defects and users complain.
Instead we get slow degradation of overall quality. All those small issues compound overtime to create a brittle systems that is difficult to debug and maintain.
My mental model of software engineering is like this. Each commit/PR is a small LEGO block. If you make them well they’ll snap well and create a stable structure that can withstand forces. If every LEGO block you make is just slightly off here and there. Your structure becomes unstable and will always have faults and will always have failures under unpredictable environmental pressures.
reply