The cope just keeps coming!
Prevent cognitive debt by manually retyping LLM-generated code
401–410 of 479 posts
Re: Prevent cognitive debt by manually retyping LLM-generated code
#402So we are reduced to code monkeys mindlessly re-typing what an LLM wrote to increase potential understanding... Whatever this approaches, it is not a state of software engineering I find desirable.
Don't worry. No one will want human code in just a few years. This bizarre fixation that humans are decent at coding is a myth. Retype what the machine tells you? I would rather garden or move rocks around.
> This bizarre fixation that humans are decent at coding is a myth.
I wonder where the LLMs got their training data from.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#403Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?
The LLM is, in many ways, smarter than you and I: it can perform feats of advanced mathematics that have eluded mathematicians for decades. It's not at all unreasonable to think that an LLM could produce an idea better than you could have, but that reading it and typing it in gives you some better understanding of how it works.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#404Earlier quoted context omitted.
> I mean in your case, you are not able to use LLMs effectively to build features, so you should type the code by hand. I never write code sitting at a computer. Mostly I write it in the car, when I have no distractions. I just type it in when I'm sitting at the computer. I've been using Claude as an experiment for some "fun" projects that I'm unlikely to release, just to see how it is. The thing is, at least for the…
I mostly do reading in front of the computer (not code, docs), but that's before I'm used to the project. Usually I spend more time on the couch than in front of the computer. Because that's where I think best. If I'm writing code, I already have the solution.
Yup, that's what I do to, although like I say I mostly write my code in the car. I work on things all over Scotland so quite often I'm spending six hours driving to do a ten minute repair, and it is *great*. No, you can't phone me, I'm driving. No, I can't just jump on your teams call real quick, I'm driving? Email? No, driving.
It is *great*.
Re: Prevent cognitive debt by manually retyping LLM-generated code
#405Also... if your workflow is "think hard, let LLM write it, read what AI wrote, think hard about what AI wrote, re-type what AI wrote, fix what AI wrote"... Where in the heck are the efficiency gains? Couldn't you just drop the LLM part of it and save the company a trillion dollars in tokens?
in code you do not care enough to read, in experimental code, one off things, tests, reading a codebase with no documentation, re jobs
Re: Prevent cognitive debt by manually retyping LLM-generated code
#406As someone who’s been programming for 20 years, I have to say that programming itself often causes a kind of brain rot. I’m very glad that I can now focus on other aspects of software development. It was only with Claude Code that I realized I never actually enjoyed programming—I enjoyed building things. You can live a perfectly mentally healthy life without programming.
> It was only with Claude Code that I realized I never actually enjoyed programming
This is so real!
Re: Prevent cognitive debt by manually retyping LLM-generated code
#407[flagged]
Re: Prevent cognitive debt by manually retyping LLM-generated code
#408I used to do this and called it "Coding with AI the Hard Way" in a nod to Zed Shaw: https://kamens.com/blog/code-with-ai-the-hard-way I no longer do and blogged my updates for fear of being seen as a luddite: https://kamens.com/blog/code-with-ai-the-hard-way-update https://kamens.com/blog/code-with-ai-the-hard-way-update-ii
Ben if you're going to blog about things with relative timestamps you need to provide a base timestamp, and I would also appreciate that for when you update the post. "3 months ago" is unhelpful without that context. Well done for registering your beliefs publicly and updating them publicly. So many people out here exist in an epistemology-free zone.
I'm seeing what looks like a date in the top-right corner of the header banner. Not sure if it was added in response to the note, so mentioning just in case!
Re: Prevent cognitive debt by manually retyping LLM-generated code
#409As someone who’s been programming for 20 years, I have to say that programming itself often causes a kind of brain rot. I’m very glad that I can now focus on other aspects of software development. It was only with Claude Code that I realized I never actually enjoyed programming—I enjoyed building things. You can live a perfectly mentally healthy life without programming.
[flagged]
Re: Prevent cognitive debt by manually retyping LLM-generated code
#410Earlier quoted context omitted.
Frontier LLMs write better code at CRUD tasks than 95% of developers today. They’ll get to 95% of most niche coding domains by December and likely all coding tasks sometime next year; 99% better at all tasks by December 2028. You may be correct now and it doesn’t matter one bit.
We’ve been hearing the drumbeat that these models are already better than $INVENT_A_NUMBER percentage of developers at $SOME_SMALL_TASK for several years. I haven’t seen that it’s actually true yet personally. What I do see is that the frontier models can get easy stuff mostly right, but they can’t maintain a small codebase such that it behaves correctly across several mutations. When the going requires a lot of cont…
I hope you're right, but hope is not a process. I'm looking at the obviously exponential charts of capabilities and don't have much to add to that hope.
Vera Rubin datacenters aren't even online yet.