[jdub]

> At Reco, we have a policy engine that evaluates JSONata expressions against every message in our data pipeline - billions of events, on thousands of distinct expressions.

The original architecture choice and price almost gave me a brain aneurysm, but the "build it with AI" solution is also under-considered.

This looks like a perfect candidate for existing, high quality, high performance, production grade solutions such quamina (independent successor to aws/event-ruler, and ancestor to quamina-rs).

There's going to be a lot of "we were doing something stupid and we solved it by doing something stupid with AI [LLM code]" in our near future. :-|

[chii]

But if the ai built solution is slightly less stupid, then it's still a win isnt it?

[legacynl]

As far as I see it, AI is the reason they're unnecessarily paying 300k/year in the first place. A human engineer was the one that identified the problem with this JS dependency, and the human told then made AI fix its' original mistake.

That's a win for human engineers, not AI.

[simultsop]

but they saved $500k. Before some humans knew about constraints in it. Now nobody knows.

Jokes aside, we will probably see everyone doing this, trying to remove human hands off of code, because they corrupt and AI does not.

Joke jokes aside why did we even code until AI?

[pullshark91]

I don't understand if you're joking or not. I hope you are...

[simultsop]

It is not me, it is the whole industry doing it

[throwa356262]

If you start with something really really horrible, chances are even an accidental change by an intern can improve it.

[skeeter2020]

it can ALWAYS get worse...