I rewrote PostHog's SQL parser, 70x faster, while barely looking at the code
84 points
3 hours ago
| 16 comments
| posthog.com
| HN
jakewins
40 minutes ago
[-]
I’ve had very good success in similar setups where you have some sort of “oracle” and can generate enormous corpuses of test data, such that you really, really trust the LLM code must work for the inputs you expect it’ll ever need to handle.

Makes me think of all the algorithms we specify in proof languages and then hand-implement in production languages - this setup could maybe let you just specify the proof of an algorithm and then let LLMs derive efficient implementations with the (slow) proof as an oracle

reply
duendefm
2 hours ago
[-]
Well despite my current anti AI sentiment, I have to admit that after reading the article, It was a good use of AI, done by someone with good technical skills. Still I have the feeling that this only works because of the vast accumulated knowledge pre-AI, and if everybody keeps going in this path, it will end up making everyone not advancing their knowledge at the pace they did before. I feel that this AI immersion is really about selling our soul to the devil for short term gains.
reply
bitlad
1 hour ago
[-]
I think AI is powertool. Period. If you give it to people who are skill, it will create a mess.

I think democratization of intelligence is going to be interesting. You could say the same with same about internet. I think it is part of evolution. May be intelligence or expertise is what does not make us special. May be it is that we are ingenious amd creative with tools and thats how we evolve.

reply
choilive
1 hour ago
[-]
There are some studies that suggest human brain sizes have been shrinking over the last 20,000 years. The theory is that as civilization developed the demand for individual humans to be independently intelligent has weakened because we developed a "collective brain" and also self-domesticated to be more cooperative.
reply
veidelis
49 minutes ago
[-]
Honestly there might be truth to it, I don't get the downvotes - why?
reply
Someone
29 minutes ago
[-]
The correlation between brain volume and intelligence is fairly weak. Neanderthals had larger brains than humans, for example. Looking outside the hominids, we have fairly smart corvids with relatively tiny brains.

That means the chain of thought “brains volume decreased, so individuals must have gotten less intelligent. Yet, societies grew smarter, so there must be herd intelligence” breaks at “so individuals must have gotten less intelligent”.

I think/guess that argument may have merit when replacing brain volume by number of neurons (https://en.wikipedia.org/wiki/List_of_animals_by_number_of_n...)

reply
steve_adams_86
1 hour ago
[-]
> democratization of intelligence

I'm not trying to be pedantic; I think this is an interesting topic and there's a worthwhile distinction to make here. It isn't really being democratized for a couple reasons (at least).

One, access to information isn't truly knowledge in and of itself. People allowing information from LLMs to pass through their brains are not necessarily retaining any of it, and their ability to synthesize and utilize disparate information from LLMs isn't inherently improved by this technology. So the premise of knowledge isn't very sturdy in my mind.

Two, LLMs function across very broad fields of capability, accuracy, content, and so on, and the best models are not accessible to many people. I find people tend to mean the technology is widely available and accessible when they say 'democratization', but that's not necessarily true nor what that word means to begin with.

True democratization would mean something more like "everyone participates in, shapes, regulates, and grows this technology with their own inputs". I don't think that's what happens at all, and in fact, it has been quite the inversion of that so far.

I mention all of this because I agree that it will be interesting to watch what happens, but I don't agree that it will be for the same reasons. I worry about it specifically because there is not an egalitarian distribution of knowledge, and it is not democratically built or shared.

reply
ekidd
1 hour ago
[-]
> May be it is that we are ingenious amd creative with tools and thats how we evolve.

And every time you use the AI to be ingenious or creative, that will be added to the training data. Then someday the AI can be ingenious and creative without you! (It might take a few more breakthroughs. But investors will literally spend trillions chasing those breakthroughs.)

The endgame here is to replace all human intelligence and labor with machines that are smarter and work cheaper. But who controls the machines?

reply
bitlad
1 hour ago
[-]
> And every time you use the AI to be ingenious or creative, that will be added to the training data That's part of evolution.

We as humans have always outsmarted the tools.

reply
jimbokun
15 minutes ago
[-]
That can be said for any technology in history that made work easier.

“Whoa slow down with this ‘writing’ technology. No one will ever remember anything if they can just write it down.”

reply
Daishiman
1 hour ago
[-]
> till I have the feeling that this only works because of the vast accumulated knowledge pre-AI

I'm not about to say that there's nothing new under the sun, but parsers are a really well-understood problem where 99.9% of people don't need frontier knowledge and wouldn't be in a position to use it anyway.

And I don't think that people doing research on parsers would ever rely on LLMs for precisely that reason. But we're not parser researchers right?

reply
duendefm
39 minutes ago
[-]
My point is, we have programming languages like C and C++, we have operating systems like Linux and FreeBSD, we have an empire of software and knowledge accumulated because of the intellectual battles fought by people before AI. With AI, we all are getting our coding easier (and are kind of being forced to), in a way that we will skip these kind of battles. That is, if we all use AI to make our job easier it will have some short term gain but we will end up as a whole ceasing to advance human knowledge with new stuff that has to come from real intellectual work. Like, I don't see people coming up with new outstanding technology if we all sucumb to be AI dependent.
reply
Daishiman
8 minutes ago
[-]
I'm not really sure that I agree. The LLM paradigm basically allows for the same development techniques, for better or worse, but amplified.

So if you were lazily copying the first blog result in Google, getting the first answer from an LLM is equivalent, but the output is actually likely to be better.

If you wanted to do your research on various techniques and evaluate alternatives, LLMs can amplify your capacity to research and to have specific considerations for your specific problem.

LLMs aren't going to solve people's natural inclination towards laziness.

Additionally, while it's true that people may read and learn less about the "lower" levels of software plumbing, it enables enormous possibilities of higher level thinking that before were limited by the amount of manpower you needed.

For example, with LLMs I can try different test sharding strategies or trivially change from factories to fixtures in large test suites. This would have been busywork or drudgery; now I can evaluate several architectural solutions which would not have been possible before.

reply
ndr
14 minutes ago
[-]
Great loop spotting!

Recently I was messing around with parquet files in Python and ended up needing to ship the results on Windows, without a Windows machine to test on.

Shipping Python to end users is half mad already, and doing it on Windows is exactly the kind of thing I don't want to spend my life maintaining.

So I figured I'd rewrite it in Go. But that meant embedding a DLL, and how would I test it? I could spin up a VM, sure. But GitHub Actions already has a Windows environment, and there was my loop: let the agent push to the repo, run tests in GHA, rinse and repeat.

In under an hour it had a full rewrite of my Python, passing every test and producing row-for-row copies of my Parquet output. And it does work on the user machine!

Spotting a loop like that is as satisfying as noticing you can walk your chess opponent into a smothered mate. Truly empowering.

reply
theLiminator
1 hour ago
[-]
This is the type of problem for which LLM generation is great for.

If you have an oracle, and your problem is largely just a pure function, it's pretty good at generating something that both works and is fast.

reply
justAnotherHero
22 minutes ago
[-]
That's great but I really wish you guys would do something about the llm integration, I tried using it two days ago to create a cohort of users using a sql query, and I was surprised to see that it said that it could not create cohorts for me and i had to resort to exporting data from a sql insight as a cohort cannot use a sql query. However the worst part was it just writing in the text input slowed down my m4 pro chip to less than 1 fps after 2 prompts and it really left a bad taste in my mouth.

Perhaps the next target for a 100x improvement

reply
ncruces
3 minutes ago
[-]
You have a grammar file in a formal language, and want to generate a faster parser in another formal language.

What's wrong with the source language that it's better to use a sufficiently smart random code generator for the target language, and then fuzz the hell out of the output of it until it behaves the same as the slow translated code, than to create a sufficiently smart compiler from the source to target languages?

I mean this sounds like if we replaced GCC with a really smart random assembly generator and a fuzzer for the output.

reply
russellthehippo
1 hour ago
[-]
The key parts of this is how not vibecoded it is. Feels like a model of how you should do software with AI. Now that we can easily set up property testing, fuzzing, etc. there's almost no reason not to.
reply
spullara
1 hour ago
[-]
that is vibecoding these days
reply
mikkelam
2 hours ago
[-]
I cannot believe they're sticking to their guns on this website design. It's awful.
reply
joshmarinacci
40 minutes ago
[-]
I love that it doesn't feel like every other vibe coded VC backed startup.
reply
kg
1 hour ago
[-]
Try clicking 'switch to website mode' on the left side
reply
nektro
42 minutes ago
[-]
thank you!
reply
my-next-account
1 hour ago
[-]
It's awesome!
reply
pixel_popping
1 hour ago
[-]
They have an excellent branding and have some balls to pull it off, it shows passion, I highly trust it even in company settings.
reply
noja
1 hour ago
[-]
I love it. So different. Slightly BeOS.
reply
softboyled
1 hour ago
[-]
Yeah. It locked up my browser. What a pile.
reply
westurner
6 minutes ago
[-]
Could the agent traces from this be used to improve sqlglot?

tobymao/sqlglot: Python SQL Parser and Transpiler; with tests and support for 30+ dialects: https://github.com/tobymao/sqlglot

Ibis depends upon sqlglot: https://github.com/tobymao/sqlglot/network/dependents

reply
lovasoa
1 hour ago
[-]
The thing I would have liked to know is why they don't use an existing fast SQL parser. Was being slightly incompatible with all existing SQL dialects a product requirement?
reply
robbie-c
1 hour ago
[-]
Our SQL is very similar to ClickHouse SQL, in that we used ClickHouse SQL as a starting point as that's what our underlying DB is. We needed to have our own parser so that we could add additional language features on top.
reply
-warren
1 hour ago
[-]
I think thats exactly what indirectly happened. This guy didnt optimize the parser. Someone else did -- years ago. That work was pulled into the LLM and made it look like magic.
reply
sam_lowry_
2 hours ago
[-]
Dunno about the parser, but you broke scrolling on your fancy website without noticing it also ;-)
reply
sayrer
56 minutes ago
[-]
ha, try to keep going. Run it under samply and Gungraun (need AMD64 for this)
reply
duke_of_vandals
1 hour ago
[-]
How long did this take?
reply
robbie-c
1 hour ago
[-]
It took about 2 days to get a proof of concept, and about a week to get something I could ship to production.

I skipped a few features for the PoC (like XML tag support, token positions), so most of the delta was adding those back in!

reply
duke_of_vandals
1 hour ago
[-]
If you didn’t need to look at the code at all, why not write it in asm instead of Rust, and make it even faster?
reply
robbie-c
1 hour ago
[-]
Ha I did consider that! But 70x is plenty fast enough (we still have to query an actual database!) and the parser runs in a shared process on untrusted input, so it wasn't worth the security risk
reply
orsorna
55 minutes ago
[-]
About 1/1000 of the duration of their interview process where they gloat about wasting your time.
reply
speedgoose
1 hour ago
[-]
There is no such thing as a legally-required cookie banner. You can read the GDPR, or ask an LLM to read it for you if you can’t read anymore.
reply
sscaryterry
1 hour ago
[-]
This is true and unkind at the same time.
reply
CrzyLngPwd
54 minutes ago
[-]
"I didn't rewrite"
reply
sscaryterry
1 hour ago
[-]
Good read, but "70x" is always misleading.
reply
robbie-c
51 minutes ago
[-]
In what way? This was a geometric mean of the improvements from a small test corpus. In production, where it only parses longer SQL that didn't hit the parser cache, the mean parse time went down by 454x, across millions of parses.
reply
hyperpape
13 minutes ago
[-]
Sounds like the real number is 454x faster, not 70x. Checkmate, nerd!
reply
sscaryterry
10 minutes ago
[-]
Go read my message again. Every time somebody states it is X time faster, and its the headline, it is pure clickbait.

Yes, you have benchmarks, they will always be synthetic. I'm not dismissing the work, just the selling of it.

You have succeeded though, I did click on it. I even said "Good read" :)

reply