May Likes Toronto1d ago

Working software developers of the Fedi, what's your relationship with AI coding (like Claude Code)?

#poll #askFedi #software

Don't like it. I don't use it for work.
53.4%
Don't like it. I have to use it for work.
12.4%
It's complicated. I don't use it for work.
5.3%
It's complicated. I have to use it for work.
10.7%
It's complicated. I happily use it for work.
7.6%
I like it. I don't use it for work.
1%
I like it. I have to use it for work.
0.3%
I like it. I happily use it for work.
6.6%
Other, comment below.
2.6%
Poll ended at .
Show threadMay Likes Toronto1d ago
Not a developer. Want to follow this poll. and see when it's over.
Poll!
76.5%
poll.
23.5%
Poll ended at .
Show threadMay Likes Toronto1d ago

I wonder what the distribution will look like if we get to 100-200+ votes.

My hypothesis is that the more casual Fedi users are more likely to use AI coding in some way.

Update:
- Started at 28% some sort of AI Coding use at ~60 votes.
- 36% at 336 votes.

Show threadThe Lack Thereof 1d ago

@mayintoronto I'm just absolutely astounded that there's this many professional coders who *aren't* required to use it in some form for work yet.

The enterprise-grade/enterprise-cost tools are far better than the basic stuff.

We have a monthly per-dev credit budget so literally on a prompt by prompt basis I have to decide which model to send it to, based on what I'm doing and how much budget I have left.

Claude Opus 4 is definitely the best. If I get all the context loaded right and give an essay-length prompt full of requirements, it will usually get something I can send out for code review with little corrections. It is also the most expensive by far.

Claude Sonnet and Claude Haiku are not worth using.

GPT-5 Codex High is next best and gets you 90% of what Claude does but at 1/3 the cost. I usually reach for it as my primary model.

GPT-5 Codex Medium is half the cost of High and I use it for simpler tasks or fixing up other models minor mistakes.

The whole gemini family is infuriating. It often does the right thing on the first prompt but when it gets things wrong it does it in the most infuriating, non-obvious way and once you see it, it absolutely refuses to take correction.

Show threadsamir, an unknown quantity9h ago
@lackthereof @mayintoronto Who is the person who would require it of me?
Show threadMay Likes Toronto9h ago
@samir Generally speaking, our employers via our VPs and managers. @lackthereof
Show threadsamir, an unknown quantity8h ago
@mayintoronto @lackthereof Right, I think this is rarer than you might think. I have never worked in a job where my manager told me how to do my job. They’ve never dictated my editor, my search engine, how I read docs, what I use for note-taking… why would they tell me I must use a specific auto-complete tool?
Show threadMay Likes Toronto8h ago

@samir I'm hearing it everywhere in my product circles. We can't get away from it in product management, and it's even worse for our dev counterparts.

@lackthereof

Show threadsamir, an unknown quantity

@mayintoronto @lackthereof I’m hearing this too, and your poll definitely shows that it’s happening, I am just not surprised it’s not that common. Perhaps it’s a regional thing. Or maybe the kind of people who socialise around their work (like you and me) are more likely to be in this kind of environment.

Personally, if my manager told me to use a different editor, it would be a reason to start looking for a new job. (I have turned down jobs because of an operating system.) Same goes for any kind of code generator, LLM-based or not.

1:47pmWeb