[__mharrison__]

My anecdotes for using LLMs to modernize legacy (20-year-old systems):

- 40x speed improvement

- Painless env setup

- 20 Second deploy

- 90+% test coverage

- Ability to quickly refactor

- Documentation

(The original system that I wrote with one other programmer 20 years ago took 1.5+ years to write. Modern rewrite: 2 days)

[kranner]

Presumably the 1.5 years for the first version involved work other than coding that the LLM rewrite didn’t entail?

[ehnto]

Business logic is usually the most substantial part of legacy systems in my experience, so I imagine so.

Not to be too negative but a lot of modern software complexity is a prison of our own making, that we had time to build because our programs are actually pretty boring CRUD apps with little complex business logic.

[croon]

I can only assume there's a ton of domain knowledge accrued over those years and beyond baked into the legacy code, that an LLM can just scoop up in a minute.

[appplication]

Not the poster you replied to but I’m sure it did. But still manual rewrite under the same constraints would be much less feasible.

[__mharrison__]

Yep, coders do more than just code.

[mandeepj]

> Modern rewrite: 2 days

How much time to verify and validate that large corpus of code that they generated? Not including back and forth to get rid of hallucinations and other mistakes.

[__mharrison__]

Two days total. Using TDD, you can move really fast with AI.

[hirvi74]

How does the code look? I am curious if there is proper usage of abstractions, or is logic just kind of all over the place?

Some part of me feels like LLM generated code is great if one cares about the solution, but leaves a lot to be desired if one actually cares about code quality. Then again, maybe I am just bad as using LLMs -- I prefer the chat over lettings LLMs do the work for me.

[__mharrison__]

It is pretty clean. It has two swappable backends. I spent a bit of time refactoring which was easy because I have tests.