Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

We rewrote JSONata with AI in a day, saved $500k/year

reco.ai

Post reply on HN
Print view View original

21–30 of 278 posts

Re: We rewrote JSONata with AI in a day, saved $500k/year

#21

Post by bawolff »

encoderer wrote: post #10
slopinthebag wrote: post #8

Earlier quoted context omitted.

It has to be satire right? Like, you aren't out of touch on this. I get engineers maybe making the argument that $300k / year on cloud is the same as 1.5 devops engineers managing in-house solutions, but for just json parsing????

I wonder if you've ever worked on a web service at scale. JSON serialization and deserialization is notoriously expensive.

They got a 1000x speed up just by switching languages.

I highly doubt the issue was serialization latency, unless they were doing something stupid like reserializing the same payload over and over again.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#22

Post by delijati »

torben-friis wrote: post #16

>The approach was the same as Cloudflare’s vinext rewrite: port the official jsonata-js test suite to Go, then implement the evaluator until every test passes. the first question that comes to mind is: who takes care of this now? You had a dependency with an open source project. now your translated copy (fork?) is yours to maintain, 13k lines of go. how do you make sure it stays updated? Is this maintainance factored…

it is all yolo from here on out ... every major ai decision we're making today feels like a bet that agi will eventually show up and clean up the mess

Re: We rewrote JSONata with AI in a day, saved $500k/year

#23

Post by encoderer »

bawolff wrote: post #21
encoderer wrote: post #10

Earlier quoted context omitted.

I wonder if you've ever worked on a web service at scale. JSON serialization and deserialization is notoriously expensive.

They got a 1000x speed up just by switching languages. I highly doubt the issue was serialization latency, unless they were doing something stupid like reserializing the same payload over and over again.

Well, for starters, they replace the RPC call with an in-process function call. But my point is anybody who's surprised that working with JSON at scale is expensive (because hey it's just JSON!) shouldn't be surprised.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#24

Post by bawolff »

torben-friis wrote: post #16

>The approach was the same as Cloudflare’s vinext rewrite: port the official jsonata-js test suite to Go, then implement the evaluator until every test passes. the first question that comes to mind is: who takes care of this now? You had a dependency with an open source project. now your translated copy (fork?) is yours to maintain, 13k lines of go. how do you make sure it stays updated? Is this maintainance factored…

I mean, my first question would be how good the test suite on this project is.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#25

Post by slopinthebag »

encoderer wrote: post #10
slopinthebag wrote: post #8

Earlier quoted context omitted.

It has to be satire right? Like, you aren't out of touch on this. I get engineers maybe making the argument that $300k / year on cloud is the same as 1.5 devops engineers managing in-house solutions, but for just json parsing????

I wonder if you've ever worked on a web service at scale. JSON serialization and deserialization is notoriously expensive.

Would it be better or worse if I had that experience and still said it's stupid?

Re: We rewrote JSONata with AI in a day, saved $500k/year

#26

Post by jcims »

ebb_earl_co wrote: post #3

> This was costing us ~$300K/year in compute, and the number kept growing as more customers and detection rules were added. Maybe I’m out of touch, but I cannot fathom this level of cost for custom lambda functions operating on JSON objects.

This is where the cost came from.

>The reference implementation is JavaScript, whereas our pipeline is in Go. So for years we’ve been running a fleet of jsonata-js pods on Kubernetes - Node.js processes that our Go services call over RPC. That meant that for every event (and expression) we had to serialize, send over the network, evaluate, serialize the result, and finally send it back.

But either way, we're talking $25k/mo. That's not even remotely difficult to believe.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#28

Post by Herring »

torben-friis wrote: post #16

>The approach was the same as Cloudflare’s vinext rewrite: port the official jsonata-js test suite to Go, then implement the evaluator until every test passes. the first question that comes to mind is: who takes care of this now? You had a dependency with an open source project. now your translated copy (fork?) is yours to maintain, 13k lines of go. how do you make sure it stays updated? Is this maintainance factored…

The full translation took 7hrs and $400 in tokens. Applying diffs every quarter using AI is much easier and cheaper. Software engineering has completely changed.

Re: We rewrote JSONata with AI in a day, saved $500k/year

#30

Post by mickael-kerjean »

A principal engineer spending his week end vibe coding some slop at a rate of 13k lines of code in 7h to replace a vendor. Is this really the new direction we want to set for our industry? For the first time ever, I have had a CTO vibe conding something to replace my product [1] even though it cost less than a day of his salary. The direction we are heading makes me want to quit, all points to software now being worthless

[1] https://github.com/mickael-kerjean/filestash

Post reply on HN