161–170 of 334 posts
For me, LLMs are joyful experiences. I think of ideas and they make them happen. Remarkable and enjoyable. I can see how someone who would rather assemble the furniture, or perhaps build it, would like to do that.
I can’t really relate but I can understand it.
> Even if I generate a 1,000 line PR in 30 minutes I still need to understand and review it. Since I am responsible for the code I ship, this makes me the bottleneck. I am not responsible for choosing whether the code I write using a for loop or while loop. I am responsible for whether my implementation - code, architecture, user experience - meets the functional and non functional requirements. It’s been well over a…
When I got my first job long ago, I found that code review does involve arguing over things like for vs while loop, or having proper grammar in comments. Thought about quitting for a sec. Now that I have more experience and manage other SWEs, I was right, that stuff was dumb and I'm glad that nobody cares anymore. I'll spend the time reviewing but only the important things.
My wife and my dad enjoy assembling furniture (the former free style, the latter off the instructions). I like the furniture assembled but I cannot stand doing it. Some of us are one way and others are the other way. For me, LLMs are joyful experiences. I think of ideas and they make them happen. Remarkable and enjoyable. I can see how someone who would rather assemble the furniture, or perhaps build it, would like t…
Earlier quoted context omitted.
I’ve heard this metaphor before and I don’t think it works well. For one, a power tool like a bandsaw is a centaur technology. I, the human, am the top half of the centaur. The tool drives around doing what I tell it to do and helping me to do the task faster (or at all in some cases). A GenAI tool is a reverse-centaur technology. The algorithm does almost all of the work. I’m the bottom half of the centaur helping t…
It seems like you're doing a lot of work to miss the actual point. Focusing on the minutiae of the analogy is a distraction from the over arching and obvious point. It has nothing to do with how you feel , it has to do with how you will compete in a world with others who feel differently. There were carpenters who refused to use power tools, some still do. They are probably happy -- and that's great, all the power to…
All previously mentioned levels produce deterministic results. Same input, same output.
AI-generation is not deterministic. It’s not even predictable. And example of big software companies clearly show what mass adoption of AI tools will look like in terms of software quality. I dread if using AI will ever be an expectation, this will be level of enshittification never before imagined.
Earlier quoted context omitted.
This is what I don’t understand: why highly-paid SWEs seem to think that their salaries will remain the same (if they even still have a job) if their role is now a glorified project manager.
Architects and engineers are not construction workers. AI can build the thing but it needs to be told exactly what to build by someone who knows how software works. I’ve spent enough time working with cross-functional stakeholders to know that the vast majority of PM (whether of the product, program, or project variety), will not be capable of running AI towards any meaningful software development goal. At best they…
Right now millions of developers are providing tons of architecture questions and answers. That's all going to be used as training data for the next model coming out in 6 months time.
This is a moat on our jobs as deep as a puddle.
If you believe LLMs will be able to do complex coding tasks, you must also concede they will be able to make the relatively simpler architecture choices easily simply by asking the right questions. Something they're already starting to be able to do.
I will do what i know gives me the best possible and fastest outcome over the long term, 5-10 year period. And that remains largely neovim and by hand. The process of typing code gives me a deeper understanding of the project that lets me deliver future features FASTER. I'm fundamentally convinced that my investment into deep long term grokking of a project will allow me to surpass primarily LLM projects over the lon…
Earlier quoted context omitted.
When I got my first job long ago, I found that code review does involve arguing over things like for vs while loop, or having proper grammar in comments. Thought about quitting for a sec. Now that I have more experience and manage other SWEs, I was right, that stuff was dumb and I'm glad that nobody cares anymore. I'll spend the time reviewing but only the important things.
Is there something about LLMs that suddenly make grammar and style irrelevant? Is your take, no human is going to read this ever again, so why bother making it pretty and consistent/readable?
In other comment, meant that other reviewers who used to nitpick have stopped for whatever reason, maybe because overall people are busier now.
This is no different then carpentry. Yes, all furniture can now be built by machines. Some people still choose to build it by hand. Does that make them less productive? Yes. Will they ever carve furniture by hand for a business? Probably not. Can they still enjoy the act of working with the wood? Yes. If you want to code by hand, then do it! No one's stopping you. But we shouldn't pretend that you will be able to do…
I’ve heard this metaphor before and I don’t think it works well. For one, a power tool like a bandsaw is a centaur technology. I, the human, am the top half of the centaur. The tool drives around doing what I tell it to do and helping me to do the task faster (or at all in some cases). A GenAI tool is a reverse-centaur technology. The algorithm does almost all of the work. I’m the bottom half of the centaur helping t…
Humans are involved with assembly only because the last bits are maniacally difficult to get right. Humans might be involved with software still for many years, but it probably will look like doing final assembly and QA of pre-assembled components.
This is no different then carpentry. Yes, all furniture can now be built by machines. Some people still choose to build it by hand. Does that make them less productive? Yes. Will they ever carve furniture by hand for a business? Probably not. Can they still enjoy the act of working with the wood? Yes. If you want to code by hand, then do it! No one's stopping you. But we shouldn't pretend that you will be able to do…
I'm still not sure about the productivity. Last time I asked a LLM to generate a lib for me it did it in a few second but the result took me the day to review and correct. About the same time it would take me to write it from scratch.
Right now the only way to save time with LLMs is to trust the output and not review it. But if you do that, you're just going to produce crappy software.
Earlier quoted context omitted.
> I think there will be a bifurcation between people who are finicky about 10 lines of code. And those finicky about high level product experiences. No ones care about a random 10 lines of code. And the focus of AI hypers on LoC is disturbing. Either the code is correct and good (allows for change later down the line) or it isn't. > We may weirdly be in a case where it's possible to single-shot a slack clone, but tak…
Nobody care until there’s an incident or security vulnerability, something doesn’t work based on some PMs assumptions of how it should work. The question to me becomes whether the PM -> engineering handoff outdated? Should they be the same person? Does it collapse to one skillet for this work?