21–30 of 72 posts
Fully agree with this, careful work is foundationally engineering. Slopping and not reviewing work is not.
It's of course impossible to have any nuance or middle ground here where you use LLMs to assist while you still focus on the engineering design decisions and the quality.
Holy reach
Couldn't take an article seriously that started with the author claiming that code he writes by hand is "100% correct" Bruh
I've gone back over most of my contributions to open source using LLMs and honestly, even though it was my best work at the time, there are big gaps that they find right away. The myth that we've been shipping perfect code for years, but you can't trust LLMs, is just subjective blindness. People can't see the issues that they can't see, definitionally. You can absolutely use the exact techniques we used to use in "th…
Earlier quoted context omitted.
I've gone back over most of my contributions to open source using LLMs and honestly, even though it was my best work at the time, there are big gaps that they find right away. The myth that we've been shipping perfect code for years, but you can't trust LLMs, is just subjective blindness. People can't see the issues that they can't see, definitionally. You can absolutely use the exact techniques we used to use in "th…
Likewise, I've found many bugs using LLMs in the small software libraries I hand wrote and considered complete and correct - even though it was my sole focus at the time and I thought I had perfected it
Weirdly, I thought the terms would be reversed… I think of a craftsman as someone who values quality over quantity, and makes everything beautiful and long lasting, while an engineer is more about productivity and tolerances and efficiency. A craftsman makes better quality but doesn’t scale the way an engineer and the factory process does, although mass produced goods sacrifice quality for quantity.
Software is ephemeral. Very little of it lasts for long. And if it does, it's legacy banking or some ossified terrible thing people are afraid to touch - not something revered. Every piece of software today will be rewritten. By 2100 much of it will be dead and gone. Like punch cards that have rotted away.
I would call myself an artisanal programmer. Software Engineers are some of the least likable people I've ever met and being associated with them is cringe. Questions like, "Why are you using Notepad++ instead of using VSCode with 100+ plugins?" in a very condescending manner gets old very quickly. They need the title of Engineer because deep down they are very insecure. On the plus side, they're usually promoted ver…
Weirdly, I thought the terms would be reversed… I think of a craftsman as someone who values quality over quantity, and makes everything beautiful and long lasting, while an engineer is more about productivity and tolerances and efficiency. A craftsman makes better quality but doesn’t scale the way an engineer and the factory process does, although mass produced goods sacrifice quality for quantity.
Earlier quoted context omitted.
I've gone back over most of my contributions to open source using LLMs and honestly, even though it was my best work at the time, there are big gaps that they find right away. The myth that we've been shipping perfect code for years, but you can't trust LLMs, is just subjective blindness. People can't see the issues that they can't see, definitionally. You can absolutely use the exact techniques we used to use in "th…
We definitely haven't been writing completely correct code in the past. But even so, the code LLMs write has more issues than the code humans write.
I find more pleasure and satisfaction by programming at a higher altitude, at the system level. This zooming out gives you a better feel for building an effective scaffold and you can iterate on ideas faster.
"Does it work" is what matters. We already know that "do this make no mistakes" works on some things. And then some things that are very "wide" e g "integrations for lots of different things" you basically write a new layer of software on top of the software in specs and .md and that yields a software project that you can mostly just add features by asking for them. But there's still deep narrow projects where creating that context is way more work than just implementing it. And then you have some projects where you can mix approaches and use the "metasoftware" for all the cicd and boring bits but not the core. I'd argue all of the above it's kind of meaningless to try to distinguish it as even if it's fully handrolled an llms still there as a search engine and task runner.