Abstractions allow for better business logic density and fewer tokens per concept/area of code. This is still very meaningful for today's LLMs.

Strictly speaking, if codebase A is doing the same thing as codebase B, but is 5-10x the LoC, you will be limited in how broadly you can effectively prompt the LLM. Queries will take longer, more technical debt+anti-patterns will creep in.

Anyone building large projects from scratch with LLMs will see plainly that they start to perform worse and slow down meaningfully as the codebase grows if you aren't pruning and compartmentalizing the code as you go.

Agree that abstractions which have a large performance cost are net-net not so worthwhile anymore. But many abstractions can be done with minimal performance hit (e.g. Rust)