This hasn’t been my experience. State of the art models available to the public still do all sorts of bandaids and bad hacks. Putting code where it doesn’t belong. Stapling types onto variable (in TypeScript) when abstractions/types already exist to use. I use it to generate code, but still have to review every line and have corrections/steering basically every time.

Maybe you have access to some other model?

> The latest frontier models will write code better than you and more elegant

They often do, but they often don’t. I regularly have to push for more elegant, or less lazy solutions.

This.

Insisting on writing code by hand when LLMs are available is not software engineering in 2026. Engineers find the most cost-effective solution for the problem at hand that meets the requirements.