Similar to bragging about LOC, I have noticed in my own field of computational fluid dynamics that some vibe coders brag about how large or rigorous their test suites are. The problem is that whenever I look more closely into the tests, the tests are not outstanding and less rigorous than my own manually created tests. There often are big gaps in vibe coded tests. I don't care if you have 1 million tests. 1 million easy tests or 1 million tests that don't cover the right parts of the code aren't worth much.
> Generally, though, most of us need to think about using more abstraction rather than less.
Maybe this was true when Programming Perl was written, but I see the opposite much more often now. I'm a big fan of WET - Write Everything Twice (stolen from comments here), then the third time think about maybe creating a new abstraction.
As someone who has switched to exclusively coded using AI after 30 years of coding by myself, I find it really weird when people take credit for the lines of code ad features that AI generates. Flexing that one "coded" tens of hundreds of thousands of lines per day is a bit cringe, seeing as though it's really just the prompt that one typed.
German General Kurt von Hammerstein-Equord (a high-ranking army officer in the Reichswehr/Wehrmacht era):
“I divide my officers into four groups. There are clever, diligent, stupid, and lazy officers. Usually two characteristics are combined.
Some are clever and diligent — their place is the General Staff.
The next lot are stupid and lazy — they make up 90% of every army and are suited to routine duties.
Anyone who is both clever and lazy is qualified for the highest leadership posts, because he possesses the intellectual clarity and the composure necessary for difficult decisions.
One must beware of anyone who is both stupid and diligent — he must not be entrusted with any responsibility because he will always cause only mischief.”
I've had this exact sentiment in the past couple months after seeing a few PRs that were definitely the wrong solution to a problem. One was implementing it's own parsing functions to which well established solutions like JSON or others likely existed. I think any non-llm programmer could have thought this up but then immediately decide to look elsewhere, their human emotions would have hit and said "that's way too much (likely redundant) work, there must be a better way". But the LLM has no emotion, it isn't lazy and that can be a problem because it makes it a lot easier to do the wrong thing.
Should we be talking about LLMs' taste and proclivities? Because these can also be prompted. You can put your Claude or Codex in the mind of someone who remembers Larry Wall and his three virtues, and it will do a fantastic job at uncovering the lacking abstractions and poor quality _in someone else's code_.
The jury is still out in my mind. Can I use these tools to create software that does not suck? Will the speed at which code can be created and modified lead to a change in our ideas of what good code looks like?
Last week I had a good idea for a change in architecture in my software that will make it much more powerful. I set a team of 12 agents on it, mostly unsupervised, with a pretty weak org structure. After a day and a half, and way too many tokens spent, they managed to build the entirely wrong thing. All tests passed.
The next few days have been spent with a much simpler structure: two teams, each of two agents, one coding (Codex is better at it these days) and one reviewing and keeping things aligned with the docs (Claude). This may have worked, I am still not sure.
My best guess right now of how good software development will look like with these tools: the effort/tokens spent on reviewing needs to be commensurate with the effort spent on coding.
As dumb as it is to loudly proclaim you wrote 200k loc last week with an LLM, I don’t think it’s much better to look at the code someone else wrote with an LLM and go “hah! Look at how stupid it is!” You’re making exactly the same error as the other guy, just in the opposite direction: you’re judging the profession of software engineering based on code output rather than value generation.
Now, did Garry Tan actually produce anything of value that week? I dunno, you’ll have to ask him.
LLMs not being lazy enough definitely feels true. But it's unclear to me if it a permanent issue, one that will be fixed in the next model upgrade or just one your agent framework/CICD framework takes care of.
e.g. Right now when using agents after I'm "done" with the feature and I commit I usually prompt "Check for any bugs or refactorings we should do" I could see a CICD step that says "Look at the last N commits and check if the code in them could be simplified or refactored to have a better abstraction"
I remember the days when we talked about mythical man-months and why LoC was not a good metric to measure programmer output. And then Ken Thompson said [1]
> One of my most productive days was throwing away 1000 lines of code.
Or the famous -2K LoC story:
> Bill Atkinson, the author of Quickdraw [...] had completely rewritten the region engine using a simpler, more general algorithm which, after some tweaking, made region operations almost six times faster. As a by-product, the rewrite also saved around 2,000 lines of code [...] it was time to fill out the management form for the first time. When he got to the lines of code part, he thought about it for a second, and then wrote in the number: -2000. [2]
I have noticed LLMs have a propensity to create full single page web applications instead of simpler programs that just print results to the terminal.
I've also struggled with getting LLMs to keep spec.md files succinct. They seem incapable of simplifing documents while doing another task (e.g. "update this doc with xyz and simply the surrounding content") and really need to be specifically tasked at simplifying/summarizing. If you want something human readable, you probably just need to write it yourself. Editing LLM output is so painful, and it also helps to keep yourself in the loop if you actually write and understand something.
Being a somewhat lazy individual myself, I'm wary of this statement. It feels too... comforting. "It's okay that I wasn't productive today, because laziness has merits".
I consider my laziness a part of who I am, and I don't demonize it, but I also don't consider it my ally - to get the things I care about done I often have to actively push against it.
143 comments
> Generally, though, most of us need to think about using more abstraction rather than less.
Maybe this was true when Programming Perl was written, but I see the opposite much more often now. I'm a big fan of WET - Write Everything Twice (stolen from comments here), then the third time think about maybe creating a new abstraction.
“I divide my officers into four groups. There are clever, diligent, stupid, and lazy officers. Usually two characteristics are combined.
Some are clever and diligent — their place is the General Staff.
The next lot are stupid and lazy — they make up 90% of every army and are suited to routine duties.
Anyone who is both clever and lazy is qualified for the highest leadership posts, because he possesses the intellectual clarity and the composure necessary for difficult decisions.
One must beware of anyone who is both stupid and diligent — he must not be entrusted with any responsibility because he will always cause only mischief.”
The jury is still out in my mind. Can I use these tools to create software that does not suck? Will the speed at which code can be created and modified lead to a change in our ideas of what good code looks like?
Last week I had a good idea for a change in architecture in my software that will make it much more powerful. I set a team of 12 agents on it, mostly unsupervised, with a pretty weak org structure. After a day and a half, and way too many tokens spent, they managed to build the entirely wrong thing. All tests passed.
The next few days have been spent with a much simpler structure: two teams, each of two agents, one coding (Codex is better at it these days) and one reviewing and keeping things aligned with the docs (Claude). This may have worked, I am still not sure.
My best guess right now of how good software development will look like with these tools: the effort/tokens spent on reviewing needs to be commensurate with the effort spent on coding.
Now, did Garry Tan actually produce anything of value that week? I dunno, you’ll have to ask him.
e.g. Right now when using agents after I'm "done" with the feature and I commit I usually prompt "Check for any bugs or refactorings we should do" I could see a CICD step that says "Look at the last N commits and check if the code in them could be simplified or refactored to have a better abstraction"
> 37K LoC per day across 5 projects
I remember the days when we talked about mythical man-months and why LoC was not a good metric to measure programmer output. And then Ken Thompson said [1]
> One of my most productive days was throwing away 1000 lines of code.
Or the famous -2K LoC story:
> Bill Atkinson, the author of Quickdraw [...] had completely rewritten the region engine using a simpler, more general algorithm which, after some tweaking, made region operations almost six times faster. As a by-product, the rewrite also saved around 2,000 lines of code [...] it was time to fill out the management form for the first time. When he got to the lines of code part, he thought about it for a second, and then wrote in the number: -2000. [2]
[1] disputed: https://skeptics.stackexchange.com/questions/43800/did-the-c...
[2] https://www.folklore.org/Negative_2000_Lines_Of_Code.html
I've also struggled with getting LLMs to keep spec.md files succinct. They seem incapable of simplifing documents while doing another task (e.g. "update this doc with xyz and simply the surrounding content") and really need to be specifically tasked at simplifying/summarizing. If you want something human readable, you probably just need to write it yourself. Editing LLM output is so painful, and it also helps to keep yourself in the loop if you actually write and understand something.
https://www.folklore.org/Negative_2000_Lines_Of_Code.html
I consider my laziness a part of who I am, and I don't demonize it, but I also don't consider it my ally - to get the things I care about done I often have to actively push against it.