I think the logic can be applied to humans as well as AI:

Sure, the AI _can_ code integrations, but it now has to maintain them, and might be tempted to modify them when it doesn't need to (leaky abstractions), adding cognitive load (in LLM parlance: "context pollution") and leading to worse results.

Batteries-included = AI and humans write less code, get more "headspace"/"free context" to focus on what "really matters".

As a very very heavy LLM user, I also notice that projects tend to be much easier for LLMs (and humans alike) to work on when they use opinionated well-established frameworks.

Nonetheless, I'm positive in a couple of years we'll have found a way for LLMs to be equally good, if not better, with other frameworks. I think we'll find mechanisms to have LLMs learn libraries and projects on the fly much better. I can imagine crazy scenarios where LLMs train smaller LLMs on project parts or libraries so they don't get context pollution but also don't need a full-retraining (or incredibly pricey inference). I can also think of a system in line with Anthropic's view of skills, where LLMs very intelligently switch their knowledge on or off. The technology isn't there yet, but we're moving FAST!

Love this era!!

What’s more likely to have a major security problem – Django’s authentication system or something custom an LLM rolled?

Because then every app is a special snowflake.

At some point you'll need to understand things to fix it, and if it's laid out in a standard way you'll get further, quicker.

Its literally the opposite.

Why would you generate sloppy version of core systems that must be included by default in every project.

It makes absolutely zero sense to generate auth/email sending/bg tasks integration/etc