The fun / creative part for me is not googling “how to slurp the contents of a file into a string” or “the exact syntax for marking some functions as unit tests” or “the correct order of symbols to specify generic type param”
It’s not “the correct html / css syntax for this basic gui I want to make”
It’s not “how to achieve the thing I’ve done 10 thousand times in other languages/frameworks, but for this language/framework”
It’s figuring the core logic out, building the thing while skipping the boring stuff, playing with abstractions that scratch my itch.
From this pov, AI is the best thing that has happened to my weekend coding. I code recreationally way more than before. Before AI, I would try a new language or framework, and I’d give up halfway because re-figuring out basic stuff for the umpteenth time is boring, it’s not fun at all. Now AI lets me skip those boring parts.
Learning Elixir and fixing a bug in an open source project went from "risk of a long slog over the course of a month with no reward" to "pepper an LLM with questions (debugging errors, understanding syntax, translating code snippets to English descriptions of behavior), write 20 lines of code by hand, write a few test cases, and submit the PR fix".
Strong agree. I've been making more progress on my passion project in the last few weeks than I have in a year, because it helped me break out of analysis paralysis.
I'm really, really, loving the agentic flow, where it digs itself out of syntax errors and the like.
Current tools: Visual Studio Code/GitHub ChatGPT5(Preview)
As an older "non-developer" it has had the opposite effect. My thirst for creation that I had back in the late 90's early 00's is back. It started slowly, but once I figured out the tooling I created almost 10 applications for myself and work in less than one month. I've done things with my Raspberry Pi I'd never thought possible (without months of tinkering), and I've created apps that bring me both personal pleasure, and workplace productivity.
It’s made me lose a lot of interest in reading / watching videos about programming. I enjoy AI for what it enables me to do, but it has changed the landscape of “content” to the point where I spent a lot less time taking in what’s out there since so much is AI related. Have chosen to stop following some channels on youtube / browse HN less.
I've been in growth for dev tools for 20 years now and it's the first time I've struggled to understand what type of content to have produced for y'all - it used to be pretty easy to figure out how to add value (tutorials, interviews, etc) - these days it's less easy to see what folks want - it's hard to do educational content that would land well because folks just talk to an LLM now to learn things. I have budget and I'm unsure exactly where to spend it, so I'd be curious to hear what you'd like to see more of - thank you. :)
I'm still not using AI much, but I'm especially wary of using it to help me with any creative task such as writing or coding. I believe "vibe coding" is the anthesis of hacker culture. What interest I've lost is probably more due to being depressed about the direction I see things heading.
The problem is that coding is often not a very creative task. Its higher levels are creative, some of the details may be creative, but there's still plenty of legwork. In other words, most of our languages are not high-level enough. This is where the AI can be helpful.
I don't use LLMs much for heavy lifting around the code. But it's an almost-excellent tool for research, finding or synthesizing examples, and generating boilerplate where other tools can't do it. "Almost", because LLMs hallucinate more often than I would like, so sometimes I have to cross-check their answers.
Quite the opposite: troubleshooting the garbage it spits out helped build confidence in my own capabilities, and now I find myself writing code more frequently than ever - and with more complexity and features than I ever dare attempt before, with no LLM assistance whatsoever.
Nothing like cleaning up someone (or in the case of LLMs, something’s) garbage code to boost ones skill and confidence.
Initially, yes. For me, it took the joy out of development. I was at the point of abandoning it but decided to try some different approaches with it. I think it’s here to stay and felt there had to be some way to leverage it without it making me depressed.
The way I’m using it now I figured out through trial and error. I form a mental model of what I want from start to finish. I then break that down into pieces, and use AI (when appropriate) to generate the code for each piece in sequence. This essentially leaves me in power of the entire development process, but the AI helps me produce the syntax much quicker than I could without it.
1. I no longer write demo code, to prove skills. It's too easily replicated by someone with an AI account.
2. I used to engage small purpose-built DSL's, languages, and systems because they were easy to adopt. Now they're at a strong disadvantage for lack of AI coverage.
3. I focus a lot more on value to the customer; opportunity is now the limiting factor, so I have the product manager hat on most of the time. So I actually do less coding, pruning almost everything that I used to do just to see if I could.
4. I do try harder problems and techniques, because with AI I can typically get to a MVP I can validate and iterate (i.e., it minimizes the stage where nothing is really working). Sometimes it works, and sometimes it just gets blocked; it's more like hunting than gardening or building.
Overall, it's made skills matter less and opportunity/connections matter more, and those are mostly outside my control. That makes it generally de-powering because though I can do much more, the value of what I can do is diminished by a larger factor.
Readit News
The fun / creative part for me is not googling “how to slurp the contents of a file into a string” or “the exact syntax for marking some functions as unit tests” or “the correct order of symbols to specify generic type param”
It’s not “the correct html / css syntax for this basic gui I want to make”
It’s not “how to achieve the thing I’ve done 10 thousand times in other languages/frameworks, but for this language/framework”
It’s figuring the core logic out, building the thing while skipping the boring stuff, playing with abstractions that scratch my itch.
From this pov, AI is the best thing that has happened to my weekend coding. I code recreationally way more than before. Before AI, I would try a new language or framework, and I’d give up halfway because re-figuring out basic stuff for the umpteenth time is boring, it’s not fun at all. Now AI lets me skip those boring parts.
Learning Elixir and fixing a bug in an open source project went from "risk of a long slog over the course of a month with no reward" to "pepper an LLM with questions (debugging errors, understanding syntax, translating code snippets to English descriptions of behavior), write 20 lines of code by hand, write a few test cases, and submit the PR fix".
I'm really, really, loving the agentic flow, where it digs itself out of syntax errors and the like.
Current tools: Visual Studio Code/GitHub ChatGPT5(Preview)
Deleted Comment
I'm still not using AI much, but I'm especially wary of using it to help me with any creative task such as writing or coding. I believe "vibe coding" is the anthesis of hacker culture. What interest I've lost is probably more due to being depressed about the direction I see things heading.
I don't use LLMs much for heavy lifting around the code. But it's an almost-excellent tool for research, finding or synthesizing examples, and generating boilerplate where other tools can't do it. "Almost", because LLMs hallucinate more often than I would like, so sometimes I have to cross-check their answers.
Nothing like cleaning up someone (or in the case of LLMs, something’s) garbage code to boost ones skill and confidence.
The way I’m using it now I figured out through trial and error. I form a mental model of what I want from start to finish. I then break that down into pieces, and use AI (when appropriate) to generate the code for each piece in sequence. This essentially leaves me in power of the entire development process, but the AI helps me produce the syntax much quicker than I could without it.
2. I used to engage small purpose-built DSL's, languages, and systems because they were easy to adopt. Now they're at a strong disadvantage for lack of AI coverage.
3. I focus a lot more on value to the customer; opportunity is now the limiting factor, so I have the product manager hat on most of the time. So I actually do less coding, pruning almost everything that I used to do just to see if I could.
4. I do try harder problems and techniques, because with AI I can typically get to a MVP I can validate and iterate (i.e., it minimizes the stage where nothing is really working). Sometimes it works, and sometimes it just gets blocked; it's more like hunting than gardening or building.
Overall, it's made skills matter less and opportunity/connections matter more, and those are mostly outside my control. That makes it generally de-powering because though I can do much more, the value of what I can do is diminished by a larger factor.
Deleted Comment