i write code because i love it. it's something that makes me genuinely happy, so why would i give that up?
And then it feels like a chore slogging through whatever it produced to verify it is correct.
Only that businesses have decided it is OK as long as they are benefitting to steal from everyone else, and basically force us to be the acting hand in all of it, or threaten us with starvation (no job, no income).
Same.
My difficulty is that for the past 8 years I've been working for (tiiiiny) SaaS business where I don't have anyone I can simply ask in-person "hey, can you show me how to 'do' all this newfangled AI agentic team coding?"; so my only direct-exposure is with the painful Copilot sidebar chat, which I now find myself allergic to.
So let's see elsewhere: while searching online for some (reputable) "agentic coding courses" my results are for the same kind of people who used to run those dodgy coding-camps from 10 years ago. I'm having difficulty finding resources for practicing SWEs like myself wanting a continuing-professional-development course experience, not a get-rich-by-buying-my-course video library from a contemptable AI booster
Even more surprisingly, my local major university (UW.edu) doesn't seem to offer any certificate courses for getting into agentic development either[1] despite offering courses on C++, Six Sigma, and actual ML/AI courses. It's maddening. I can't be the only one with this problem...
[1] https://www.pce.uw.edu/search?type=certificate&programType=c...
See how it fails or succeeds. Look at the supported features, try them out, think about how you might use them in your workflow.
Before you know it, you'll be proficient.
You have to learn how to self-teach.
Doesn't have to be stressful. Plan to throw away whatever happens. Do it in a VM if your nerves demand it. No reason it can't be fun.
...so I've been avoidant of the whole thing ever since 2023, burying my head in the sand to avoid those feelings of anxiety and uncertainty-about-the-future, and it now makes it difficult for me to engage with the topic head-on.
I dove in in ~2023, and I'm about as deep in it as one can be. The better I get at it, and the better the agents get, the less time I spend even doing what I do - one prompt will often take 3+ hours. I often keep 8+ agents churning for the whole workday (and leave them running when I leave, too, and it's very often that they'll work from 4pm to midnight or later). I was responsible for 499 commits last week (very little new functionality, though), and I felt pretty useless at the end of it. I keep thinking I should code something, because coding feels productive in comparison, but going by results, it's pretty far from economical to write code by hand, and quickly approaching as bad as shipping goods by foot.
So far in the LLM coding revolution I still feel like it's software development. I just work with systems on the level of features and architecture instead of flow control statements. Some day we might lose that too, but I think it will take a while.
That's kinda at the level I enjoy though - where I get to think-through things when figuring out exhaustiveness and correctness; introducing refinement-types into a codebase that's previously nothing but ints-and-strings; and trying out new and cutting-edge language-features directly.
I know I can prompt Claude etc into trying to do those things, but from what I've seen from other people doing it the result is somewhat of a mess - or just plain inelegant.
-----
May I ask how well Claude/Copilot/etc works with FP languages instead? So far - and back in early 2024 - I've only messed-around with asking ChatGPT to generate Haskell programs and the results were hallucinated gibberish.
Anyway I can say this - the free web interface to ChatGPT in 2024 vs what you get with agent harnesses and the latest large models now is like comparing a wombat fetus to a college graduate.
Get one of the 20 or so dollar subscriptions, install Claude code, codex or similar and start by explaining what program you want to make and which language you want to do it in. Have it make a plan first, and do some back-and-forth to refine it until you're ready to let it implement.
If your experience is from ChatGPT two years ago I think you will be floored by the results, even in Haskell.
Maybe that's "enough" for the business to survive. But it surely won't be the reason it succeeds. It can still succeed for other factors though, but the business has given up on one path to success, which is making better software than the competition.