Comment by tokioyoyo
4 hours ago
>How do you get the greatest quantity of maintainable, high quality code within a given token budget?
Doesn't matter as much. The cost of "maintenance" is going down, from what I can see internally, from other companies, and every story i'm reading from other organizations as well. Token budgets are changing, but model quality and effectiveness are going up as well.
> We've also been hearing for years that LLMs are going to automate away software development entirely, but software job postings are steadily rising.
I think this has been contested from day 1. SE jobs might be automated, but jobs might increase, if there's possibility of starting new companies / new investments / etc.
I'm still not clear on what you're really saying. If a human programmer's input doesn't matter at all, then anyone should be able to prompt a model until it spits out the software they want. That might work today for building fun tech demos, but I don't see it happening on projects that have a minimum bar for security/reliability and long-term maintenance. Would you say, for example, a team of 10 managers with no software experience can be as successful as a team of 10 expert programmers at building a large project like an operating system, with both teams having access to the same AI models and budget?