I read such articles more or less every day.
This article would be 100% correct if it came out 1 year ago, 75% correct 9 months ago, 50% correct 3 months ago and it's probably 25% correct now if not less.
I totally understand where this is coming from. I too am struggling with accepting that my 30+ years of programming experience is quickly becoming obsolete. I'm losing sleep about this, it's tough.
But just go ahead and give the latest models (Opus 5.5 / Astra 6 as of today) another try.
See what they are capable of and read the code which they produce.
Any problem area, low level C++ or high level Typescript or Clojure or a weird combination of these..
Don't be shy, give them a big task, let them build an entire app, UI and all..
Now compare the output to Opus 4 or gpt-5 from 1 year ago - when they couldn't put together a single function without it being weird and buggy.
This is exactly my problem, not that the models are very good already, but how fast they got so good.
So if coding is not solved yet, it'll get there very soon.
I use the latest models every day for app development, it does still make many mistakes and poor decisions. Just today I dealt with an issue where it allowed a silent failure that would delete all of the users data without anyone noticing. The code it writes for one task is usually pretty good, but it still doesn’t always follow conventions well even if you’ve documented them. It also has no sense for long-term architecture or organization, or when to make tradeoffs for less complexity because it’s a temporary or prototype feature that needs to stay easy to change. I’ve found that if I do even 3 months of pure agentic coding with no code reviews, it’s aged 10x faster than a human coded codebase so it’s like a 30 month legacy codebase now. I know people who are obsessed with AI coding and they’re throwing away projects they’ve built over a year and starting over because it’s become too slow to make changes.
What kind of coding are you using these models for? Most of the people I know who share your perspective never go beyond the prototyping stage. I’d be curious to hear from anyone who’s been AI coding for more than six months, shipping it to real users, and isn’t looking at their code at all.
I'd be curious to hear from anyone who's been AI coding for more than six months, shipping it to real users, and isn't looking at their code at all.
I haven't opened my IDE in months.
I only skim the MRs to make sure there are no glaring issues.
Success is a good set of skills, a good up front design for your feature, architecture docs in your repo, lots of automated linting, unit testing, AI MR reviews, and black box e2e testing.
I doubt I'll ever _have_ to write a line of code again.
All of my time is spent juggling 5-20 agents, mostly planning and responding to the agents escalations.
GPT 6 Sol / GPT 6 Luna are my bread and butter and spec-driven design works great.
Like 75% of the small issues that used to take me a few hours or half a day in 2021 take me like 15 minutes to ship now start to finish, and I can ship them while doing other things.
Context matters here. Are you a freelance website designer? Are you a CRUD app codemonkey? Do you work for a glorified data integrator, maybe in the healthcare industry? Are you an embedded engineer? Do you write code that if something goes wrong someone will die?
I can also ship slop if the stakes are 0. The code I write has stakes. Thousands of dollars per false positive, which happens to be approximately the entire margin that we’re operating within. If a false positive occurs and I can’t explain it because I shipped slop, then it’s curtains for me - and our contract.
I think "March of 9s" helps to describe this situation. Some devs seems to be happy with just one 9 as it suffice for their use-case while for others one 9 means that they would loose client's data 10% of the time or some other catastrophic consequence.
temp00345 · · focus · HN ↗
I totally understand where this is coming from. I too am struggling with accepting that my 30+ years of programming experience is quickly becoming obsolete. I'm losing sleep about this, it's tough.
But just go ahead and give the latest models (Opus 5.5 / Astra 6 as of today) another try. See what they are capable of and read the code which they produce. Any problem area, low level C++ or high level Typescript or Clojure or a weird combination of these..
Don't be shy, give them a big task, let them build an entire app, UI and all..
Now compare the output to Opus 4 or gpt-5 from 1 year ago - when they couldn't put together a single function without it being weird and buggy.
This is exactly my problem, not that the models are very good already, but how fast they got so good. So if coding is not solved yet, it'll get there very soon.
an0malous · · focus · HN ↗
What kind of coding are you using these models for? Most of the people I know who share your perspective never go beyond the prototyping stage. I’d be curious to hear from anyone who’s been AI coding for more than six months, shipping it to real users, and isn’t looking at their code at all.
ysajang · · focus · HN ↗
spicyusername · · focus · HN ↗
I haven't opened my IDE in months. I only skim the MRs to make sure there are no glaring issues.
Success is a good set of skills, a good up front design for your feature, architecture docs in your repo, lots of automated linting, unit testing, AI MR reviews, and black box e2e testing.
I doubt I'll ever _have_ to write a line of code again.
All of my time is spent juggling 5-20 agents, mostly planning and responding to the agents escalations.
GPT 6 Sol / GPT 6 Luna are my bread and butter and spec-driven design works great.
Like 75% of the small issues that used to take me a few hours or half a day in 2021 take me like 15 minutes to ship now start to finish, and I can ship them while doing other things.
datsci_est_2015 · · focus · HN ↗
I can also ship slop if the stakes are 0. The code I write has stakes. Thousands of dollars per false positive, which happens to be approximately the entire margin that we’re operating within. If a false positive occurs and I can’t explain it because I shipped slop, then it’s curtains for me - and our contract.
maxnevermind · · focus · HN ↗