Some famous sculptors had an atelier full of students that helped them with mundane tasks, like carving out a basic shape from a block of stone.
When the basic shape was done, the master came and did the rest. You may want to have the physical exercise of doing the work yourself, but maybe someone sometimes likes to do the fine work and leave the crude one to the AI.
In my case, it really depends what. I enjoy designing systems and domain-specific languages or writing libraries that work the way I think they should work.
On the other hand, if e.g. I need a web interface to do something, the only way I can enjoy myself is by designing my own web framework, which is pretty time-consuming, and then I still need to figure out how to make collapsible sections in CSS and blerghhh. Claude can do that in a few seconds. It's a delightful moment of "oh, thank god, I don't have to do this crap anymore."
There are many coding tasks that are just tedium, including 99% of frontend development and over half of backend development. I think it's fine to throw that stuff to AI. It still leaves a lot of fun on the table.
In my case, I enjoy writing code too, but it's helpful to have an assistant I can ask to handle small tasks so I can focus on a specific part that requires attention to detail
Or “can you prototype doing A via approaches X, Y, and Z, and show me what each looks like?”
I love to prototype various approaches. Sometimes I just want to see which one feels like the most natural fit. The LLM can do this in a tenth of the time I can, and I just need to get a general idea of how each approach would feel in practice.
> Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.
In my experience most LLMs are going to answer this with some form of "Absolutely!" and then propose a square-peg-into-a-round-hole way to do it that is likely suboptimal vs using a different library that is far more suited to your problem if you didn't guess the right fit library to begin with.
The sycophancy problem is still very real even when the topic is entirely technical.
Gemini is (in my experience) the least likely to lead you astray in these situations but its still a significant problem even there.
Just be careful if functionality varies between library y version 2 and library y version 3, or if there is a similarly named library y2 that isn't the same.
You may get possibilities, but not for what you asked for.
You really get enjoyment writing a full CRUD HTTP API five times, one for each endpoint?
I don't :) Before I had IDE templates and Intellisense. Now I can just get any agentic AI to do it for me in 60 seconds and I can get to the actual work.
Why do you need a full crud http api for? Just loading the data straight from the database? Usually I've already implemented that before and I just copy paste the implementation and doing some VIM magic. And in Frameworks like Rails or Laravel, it may be less than 10 lines of code. More involved business logic? Then I'm spending more time getting a good spec for those than implementing the spec.
I don't want LLMs, AI, and eventually Robots to take over the fun stuff. I want them to do the mundane, physical tasks like laundry and dishes, leave me to the fun creative stuff.
But as we progress right now, the hype machine is pushing AI to take over art, photography, video, coding, etc. All the stuff I would rather be doing. Where's my house cleaning robot?
I would like to go even further and say: Those things, art, photography, video, coding ... They are forms of craft, human expression, creativity. They are part of what makes life interesting. So we are in the process of eliminating the interesting and creative parts, in the name of profit and productivity maxing (if any!). Maybe we can create the 100th online platform for the same thing soon 10x faster! Wow!
Of course this is a bit too black&white. There can still be a creative human being introducing nuance and differences, trying to get the automated tools to do things different in the details or some aspects. Question is, losing all those creative jobs (in absolute numbers of people doing them), what will we as society, or we as humanity become? What's the ETA on UBI, so that we can reap the benefits of what we automated away, instead of filling the pockets of a few?
Claude is very good at unfun-but-necessary coding tasks such as writing docstrings and type hints, which is a prominent instance of "laundry and dishes" for a dev.
Disagree. Claude makes the same garbage worthless comments as a Freshman CS student. Things like:
// Frobbing the bazz
res = util.frob(bazz);
Or
// If bif is True here then blorg
if (bif){
blorg;
}
Like wow, so insightful
And it will ceaselessly try to auto complete your comments with utter nonsense that is mostly grammatically correct.
The most success I have had is using claude to help with Spring Boot annotations and config processing (Because documentation is just not direct enough IMO) and to rubber duck debug with, where claude just barely edges out the rubber duck.
Well it would be funnier if dishwashers, washing machines and dryers didn't automate that ages ago. It's literally one of the first things robots started doing for us.
Me writing code is me spending 3/4 of my time wading through documentation and google searches. It's absolutely hell on my ADD. My ability to memorize is absolutely garbage. Throughout my career I've worked in like 10 different languages, and in any given project I'm usually working in at least 3 or 4. There's a lot of "now what is a map operation in this stupid fucking language called again?!"
Claude writing code gets the same output if not better in about 1/10 of the time.
That's where you realize that the writing code bits are just one small part of the overall picture. One that I realize I could do without.
May be a domain issue? If you're largely coding within a JS framework (which most software devs are tbf) then that makes total sense. If you're working in something like fintech or games, perhaps less so.
My last job was a mix of Ruby, Python, Bash, SQL, and Javascript (and CSS and HTML). One or two jobs before that it was all those plus a smattering of C. A few jobs before that it was C# and Perl.
I would say notetaking would be a much bigger help than Claude at this point. There's a lot of methods to organize information that I believe would help you, better than an hallucination machine.
Notetaking with ADHD is another sort of hell to be honest.
I absolutely can attest to what parent is saying, I have been developing software in Python for nearly a decade now and I still routinely look up the /basics/.
LLM's have been a complete gamechanger to me, being able to reduce the friction of "ok let me google what I need in a very roundabout way my memory spit it out" to a fast and often inline llm lookup.
Recently I've been experimenting with using multiple languages in some projects where certain components have a far better ecosystem in one language but the majority of the project is easier to write in a different one.
For example, I often find Python has very mature and comprehensive packages for a specific need I have, but it is a poor language for the larger project (I also just hate writing Python). So I'll often put the component behind a http server and communicate that way. Or in other cases I've used Rust for working with WASAPI and win32 which has some good crates for it, but the ecosystem is a lot less mature elsewhere.
I used to prefer reinventing the wheel in the primary project language, but I wasted so much time doing that. The tradeoff is the project structure gets a lot more complicated, but it's also a lot faster to iterate.
Plus your usual html/css/js on the frontend and something else on the backend, plus SQL.
Go for the backend, something javascripty for the front end. You're already at two. Depending if you count HTML, CSS or SQL as "languages", you're up to a half dozen pretty quick.
3 or 4 can very easily accumulate. For example: HTML, CSS as must know, plus some JS/TS (actually that's 2 langs!) for sprinkles of interactivity, backend in any proper backend language. Oh wait, there is a fifth language, SQL, because we need to access the database. Ah and those few shell scripts we need? Someone's gotta write those too. They may not always be full programming languages, but languages they are, and one needs to know them.
I sometimes think of it as a sculptor analogy.
Some famous sculptors had an atelier full of students that helped them with mundane tasks, like carving out a basic shape from a block of stone.
When the basic shape was done, the master came and did the rest. You may want to have the physical exercise of doing the work yourself, but maybe someone sometimes likes to do the fine work and leave the crude one to the AI.
In my case, it really depends what. I enjoy designing systems and domain-specific languages or writing libraries that work the way I think they should work.
On the other hand, if e.g. I need a web interface to do something, the only way I can enjoy myself is by designing my own web framework, which is pretty time-consuming, and then I still need to figure out how to make collapsible sections in CSS and blerghhh. Claude can do that in a few seconds. It's a delightful moment of "oh, thank god, I don't have to do this crap anymore."
There are many coding tasks that are just tedium, including 99% of frontend development and over half of backend development. I think it's fine to throw that stuff to AI. It still leaves a lot of fun on the table.
In my case, I enjoy writing code too, but it's helpful to have an assistant I can ask to handle small tasks so I can focus on a specific part that requires attention to detail
Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.
Or “can you prototype doing A via approaches X, Y, and Z, and show me what each looks like?”
I love to prototype various approaches. Sometimes I just want to see which one feels like the most natural fit. The LLM can do this in a tenth of the time I can, and I just need to get a general idea of how each approach would feel in practice.
24 replies →
> Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.
In my experience most LLMs are going to answer this with some form of "Absolutely!" and then propose a square-peg-into-a-round-hole way to do it that is likely suboptimal vs using a different library that is far more suited to your problem if you didn't guess the right fit library to begin with.
The sycophancy problem is still very real even when the topic is entirely technical.
Gemini is (in my experience) the least likely to lead you astray in these situations but its still a significant problem even there.
1 reply →
Just be careful if functionality varies between library y version 2 and library y version 3, or if there is a similarly named library y2 that isn't the same.
You may get possibilities, but not for what you asked for.
3 replies →
You really get enjoyment writing a full CRUD HTTP API five times, one for each endpoint?
I don't :) Before I had IDE templates and Intellisense. Now I can just get any agentic AI to do it for me in 60 seconds and I can get to the actual work.
Why do you need a full crud http api for? Just loading the data straight from the database? Usually I've already implemented that before and I just copy paste the implementation and doing some VIM magic. And in Frameworks like Rails or Laravel, it may be less than 10 lines of code. More involved business logic? Then I'm spending more time getting a good spec for those than implementing the spec.
“I want my AI to do laundry and dishes so I can code, not for my AI to code so I can do laundry and dishes”
This sums up my feelings almost exactly.
I don't want LLMs, AI, and eventually Robots to take over the fun stuff. I want them to do the mundane, physical tasks like laundry and dishes, leave me to the fun creative stuff.
But as we progress right now, the hype machine is pushing AI to take over art, photography, video, coding, etc. All the stuff I would rather be doing. Where's my house cleaning robot?
I would like to go even further and say: Those things, art, photography, video, coding ... They are forms of craft, human expression, creativity. They are part of what makes life interesting. So we are in the process of eliminating the interesting and creative parts, in the name of profit and productivity maxing (if any!). Maybe we can create the 100th online platform for the same thing soon 10x faster! Wow!
Of course this is a bit too black&white. There can still be a creative human being introducing nuance and differences, trying to get the automated tools to do things different in the details or some aspects. Question is, losing all those creative jobs (in absolute numbers of people doing them), what will we as society, or we as humanity become? What's the ETA on UBI, so that we can reap the benefits of what we automated away, instead of filling the pockets of a few?
Claude is very good at unfun-but-necessary coding tasks such as writing docstrings and type hints, which is a prominent instance of "laundry and dishes" for a dev.
>writing docstrings and type hints
Disagree. Claude makes the same garbage worthless comments as a Freshman CS student. Things like:
// Frobbing the bazz
res = util.frob(bazz);
Or
// If bif is True here then blorg
if (bif){ blorg; }
Like wow, so insightful
And it will ceaselessly try to auto complete your comments with utter nonsense that is mostly grammatically correct.
The most success I have had is using claude to help with Spring Boot annotations and config processing (Because documentation is just not direct enough IMO) and to rubber duck debug with, where claude just barely edges out the rubber duck.
1 reply →
“Sorry, the autogenerated api documentation was wrong because the ai hallucinated the docstring”
3 replies →
Well it would be funnier if dishwashers, washing machines and dryers didn't automate that ages ago. It's literally one of the first things robots started doing for us.
Soon you'll realize you're the "AI". We've lost control.
Me writing code is me spending 3/4 of my time wading through documentation and google searches. It's absolutely hell on my ADD. My ability to memorize is absolutely garbage. Throughout my career I've worked in like 10 different languages, and in any given project I'm usually working in at least 3 or 4. There's a lot of "now what is a map operation in this stupid fucking language called again?!"
Claude writing code gets the same output if not better in about 1/10 of the time.
That's where you realize that the writing code bits are just one small part of the overall picture. One that I realize I could do without.
May be a domain issue? If you're largely coding within a JS framework (which most software devs are tbf) then that makes total sense. If you're working in something like fintech or games, perhaps less so.
My last job was a mix of Ruby, Python, Bash, SQL, and Javascript (and CSS and HTML). One or two jobs before that it was all those plus a smattering of C. A few jobs before that it was C# and Perl.
I would say notetaking would be a much bigger help than Claude at this point. There's a lot of methods to organize information that I believe would help you, better than an hallucination machine.
Notetaking with ADHD is another sort of hell to be honest.
I absolutely can attest to what parent is saying, I have been developing software in Python for nearly a decade now and I still routinely look up the /basics/.
LLM's have been a complete gamechanger to me, being able to reduce the friction of "ok let me google what I need in a very roundabout way my memory spit it out" to a fast and often inline llm lookup.
6 replies →
How do you end up with 3 to 4 languages in one project?
Typescript on the frontend, Python on the backend, SQL for the database, bash for CI. This isn't even counting HTML/CSS or the YAML config.
4 replies →
Recently I've been experimenting with using multiple languages in some projects where certain components have a far better ecosystem in one language but the majority of the project is easier to write in a different one.
For example, I often find Python has very mature and comprehensive packages for a specific need I have, but it is a poor language for the larger project (I also just hate writing Python). So I'll often put the component behind a http server and communicate that way. Or in other cases I've used Rust for working with WASAPI and win32 which has some good crates for it, but the ecosystem is a lot less mature elsewhere.
I used to prefer reinventing the wheel in the primary project language, but I wasted so much time doing that. The tradeoff is the project structure gets a lot more complicated, but it's also a lot faster to iterate.
Plus your usual html/css/js on the frontend and something else on the backend, plus SQL.
Go for the backend, something javascripty for the front end. You're already at two. Depending if you count HTML, CSS or SQL as "languages", you're up to a half dozen pretty quick.
i find it's pretty rare to have a project that only consists of one or two languages, over a certain complexity/feature threshold
3 or 4 can very easily accumulate. For example: HTML, CSS as must know, plus some JS/TS (actually that's 2 langs!) for sprinkles of interactivity, backend in any proper backend language. Oh wait, there is a fifth language, SQL, because we need to access the database. Ah and those few shell scripts we need? Someone's gotta write those too. They may not always be full programming languages, but languages they are, and one needs to know them.
HTML, CSS, Javascript?
Oh my sweet summer child...