[ActionHank]

> The technology isn't there yet. Yes

> All signs point to it rapidly progressing towards this inflection. Not really

> Current agents are insanely good, every decent programmer using them knows this. Also not really

If you find them "insanely good" you were likely doing work that was already very repetitive or broadly implemented by others.

They have their uses, but it isn't as pervasive as people believe.

[catigula]

Tell me you haven't extensively used Claude Code or Codex GPT-5 without telling me.

[ActionHank]

Used both, they're great for boilerplate. Anything more they breakdown.

[catigula]

Okay well I and many other experienced engineers disagree so the only remaining conclusion is that you're misusing the technology.

[dinkumthinkum]

Argumentum ad populum. What kind of experience to those engineers? That matters. Another possible conclusion is that the parent was talking about use cases that are not simple web apps or marketing pages but real issues in large software.

[catigula]

Again you're taking your own circumstance or even patent inability and extending that to the entire technology.

You've set yourself up such that all I need to do is go "I'm developing complex veterinary software including integrations with laboratory equipment" and you're completely falsified. Why expose yourself like this instead of being intellectually humble?

[ActionHank]

You're the one who has extended their limited experience to all of software engineering.

The only reason that anyone has engaged with you here is because you're being intellectually arrogant.

[ActionHank]

Yes, exactly this.

Most of my day job is not about bashing out nextjs websites. In fact if I did that one day a year it would be a lot.

[catigula]

You could assign me a task from your job and I could trivially complete it using agents. However, I will charge consulting rates.

[handfuloflight]

What breaks down is developer patience faced with a new paradigm.