There is currently some AI scraper that uses residential IP addresses and a variety of techniques to conceal itself that likes downloading Swagger generated docs over… and over… and over.
Plus hitting the endpoints for authentication that return 403 over and over.
I've found it's terrible at digesting a few codebases I've needed to deal with (to wit, 2007-era C# which used lots of libraries which were popular then, and 1993-era Visual Basic which also used from third party library that no LLM seems to understand the first thing about).
> This appears to be a custom template system from the mid-2000s era, designed to separate presentation logic from PHP code while maintaining database connectivity for dynamic content generation.
That's great. Just yesterday I spoke with a developer who refutes Rector on old codebases, instead having an LLM simply refactor his PHP 5.6 to 8.(3 I think). He doesn't even check in Rector anymore. These are all bespoke business scripts that his team have been nursing for two decades. He even updated the Codeigniter framework it's all running on.
I suspect the problem with VB is that VB 4 and 5 (which I think was that era) were so closely tied to the IDE it is difficult to work out what is going on without it.
(I did Delphi back when VB6 was the other option so remember this problem well)
I generally use LLMs to generate Python (or TypeScript) because the quality and maintainability is significantly better than if I ask it to, for example, pump out C. They really do not perform very well outside of the most "popular" languages.
Er... we sit in prefab homes? Trailers are generally considered to be the worst possible quality of home construction and actually lose value instead of the normal appreciation real estate has.
We're definitely worse off when fabric now is mostly synthetic fabrics that flood the environment with microplastics, and last a much shorter amount of time. Of course, that's good for the fashion industry since it means they can sell more often.
The examples given are using tools to do well-defined, repeatable processes. So far, despite many attempts by upper management to make software the same way, it hasn't happened, and AI doesn't appear to be any different.
I don't see a huge difference between people writing in a high-level language and people writing complex prompts.
As someone coding since 1986, I certainly see it on the time to get something done.
AI agents isn't coding in Common Lisp home made macro DSL, is me doing in one hour doing something that could have taken a couple of days, even if I have to fix some slop along the way.
Thus I can already see the trend that started with MACH architecture and SaaS products, to go even further decreasing the team sizes required for project delivery.
Projects I used to be part of a 10 people team, are started to be sized into 5 or less.
reply