Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Offloading the boring parts is fine, but the satisfaction has to come from somewhere. When the agents do the interesting work too, the job becomes supervision.by Kvarnek
- I'm enjoying myself, but then again I'm not currently employed, so not in your target audience.
Related: Anyone looking for a nerd in Berlin, mit B1 Deutsch?
by ben_w - Been coding since I was a kid, MSc computer science, into programming languages (https://www.firefly-lang.org/).
We tried a few agentic coding tools at work, but they didn't really help.
Along came a project that required us to build a custom harness. One day we added some very basic coding tools to the harness at a whim, and it just immediately (and surprisingly) blew away everything we'd tried.
Now we do most coding through that, and it's a clear productivity boost (2x?). It still requires hand holding and review, and some amount of manual fixing.
But being able to build things much faster is a lot of fun.
- Does a burger flipper enjoy flipping burgers all day? - Not unless you're a robot. But Making a Gourmet burger without time pressure? - yes No it is not enjoyable if you have enjoyed coding by hand earlier and like your craft. Maybe for some grunt work or work that you could never do it is great. I've given up trying to enjoy at professional work.by conqrr
- Thanks for asking the question.
Preface: I do think the nature of the work is changing, now that LLMs are capable code generators. And I'll admit that I started working with LLMs because of FOMO, but also to keep my skills sharp in an evolving market. I'm not 100% certain this will pan out, but I do think that working with LLMs is a skill unto itself, and I feel that I'm much better at it now than I was when I started (in earnest, roughly) a year ago.
Q: What's my setup like? A: I'm using both Claude Code and opencode w/ DeepSeek flash. Recently I've started providing the task context to both simultaneously, and then have one act as a real-time reviewer, and one as implementer. I don't consistently use one or the other for implementer, and I'm still learning their capabilities and "who's good at what." But this allows me to get one model to provide an instantaneous code review to the other, as soon as the one model is done writing the code. I set my permissions for both to ask every time on every action: Read, Write, Bash, etc. I grew up playing turn-based RPGs, so I prefer turn-based battle to real-time.
Q: What kind of work I offload, vs do myself. A: Almost all of the code is written by an LLM, but, since I'm reading and rejecting a lot of code, and basically micro-managing them, I feel that the code that's generated is roughly what I would have written myself. Work that I don't offload is any kind of email or communication, or non-code writing, with the exception of README files, and the prose session summaries I have them write.
Q: How do I make it enjoyable? A: I make it enjoyable by finding new ways to work with the LLMs, and specifically, getting them to produce better quality code. The real-time code review process I outlined above is one method, but I've also found that the LLM will write better code when given a "guiding principles" document.
HTH
by ebcode - Per-AI I was pretty picky about the right code „esthetics“ and had joy in finding better patterns and solutions to have understandable and maintainable code. This led to me being often slow and never finishing my side projects as soon as the boring parts started.
Since I code with Claude (using codehydra[1]), I have accepted that the code itself is much worse. But I found joy in working at a much higher architecture level. This led me to finish my side projects and being much faster.
It is very different, but I can find statisfaction in both. Since I do not think AI will go away, I fully went the AI way and rarely looking at any code anymore. But changing my workflows to work on architecture, design and most important verification strategies for the agent generated code.
by stefanhoelzl - As I've more reliably produced reasonable quality code with automation I've found my joy coming from coding solutions to my own day-to-day problems and less to do with solving the problems I'm employed to solve.
It's not a bad thing IMO, the work is still getting done to a high standard but I have to look elsewhere for the satisfaction that used to come from doing my job well.
by tonytamps - For sure! I offload most work, except the "idea", rarely any domain-specific logic, and rarely any core design / architecture.
Mostly I treat the coding agent genie as a code calculator, building a plan, writing code, running tests, reviewing other code with scripts...
Fine to allow the genie to pick an idea from a queue of work, "what is most urgent and important" but not fine to go with whatever the genie thinks should be done - that's a fast track to building something you don't need yet.
I also run a pair-programming session once a week with my team where we direct the genie as a "third" person. It's important to me that we still socialize around the work, even if the genie is involved. Sitting around the pile of code on the table and riffing together is fun. Just because every team member has Claude doesn't mean we stop gathering around the table once a week.
Generally though, the enjoyment comes from the same problem-solving enjoyment I had when writing code before coding agents. It's fun to create things, fun to fix things.
The challenge is managing the addiction. I try to be done with any coding focused task by 2 pm, that let's me wind down and avoid any late into the evening wrap up. I'll spend the final hours of the workday reorganizing plans, reviewing PRs and admin tasks like email, IMs, etc..
Remember even though your enterprise is paying for your tokens, they are extracting 2x, 3x, 10x maybe even 20x the value from you with the heightened productivity from coding agents. If you have equity, let it rip ha but if you don't, take some of that productivity back for yourself.
by TomEleff