Enabling Codex to Analyze Two Decades of Hacker News Data (modolap.com)

by ronfriedhaber 30 comments 87 points
Read article View on HN

30 comments

[−] zeroxfe 43d ago
I've done this kind of thing many times with codex and sqlite, and it works very well. It's one prompt that looks something like this:

- inspect and understand the downloaded data in directory /path/..., then come up with an sqlite data model for doing detailed analytics and ingest everything into an sqlite db in data.sqlite, and document the model in model.md.

Then you can query the database adhoc pretty easily with codex prompts (and also generate PDF graphs as needed.)

I typically use the highest reasoning level for the initial prompt, and as I get deeper into the data, continuously improve on the model, indexes, etc., and just have codex handle any data migration.

[−] rizzo94 42d ago
[dead]
[−] huflungdung 43d ago
[dead]
[−] Brajeshwar 43d ago
The “Hacker News - Complete Archive” on Hugging Face,[1] recently popped up here. “The data is stored as monthly Parquet files sorted by item ID, making it straightforward to query with DuckDB, load with the datasets library, or process with any tool that reads Parquet.”

Out of curiosity, I tinkered with it using Claude to see trends and patterns (I did find a few embarrassing things about me!).

1. https://huggingface.co/datasets/open-index/hacker-news

[−] mike_hearn 43d ago
I don't quite understand how Modolap differs from just asking AI to use any other OLAP engine? Both your website and the github readme just emphasise that it's idiosyncratic and your personal approach, without explaining what that is or why anyone should care.
[−] ronfriedhaber 43d ago
Appreciate the feedback. I shall certainly revamp the README; it is rather stale.

> "how Modolap differs from just asking AI to use any other OLAP engine"

There presently exist two components, the OLAP query engine and the remote infrastructure service. The service enables systems like Codex (or developers as well) to manage datasets, maintain version control over queries, and offload the computational burden to dedicated machines. This is especially beneficial given the current trend of running agents inside micro-VMs.

In addition, it is designed with AI usage in mind. There is significant value in co-design. One could argue that models can use Polars or DuckDB just as well, and that there is no room for improvement, but I do not think this is true.

[−] esafak 43d ago
I don't get the value proposition either; your landing page is underdeveloped. Tracking the query history is trivial. Offloading computation could be done with Polars Cloud or MotherDuck. Can you expand on the "manage datasets" part?
[−] bastawhiz 43d ago
What room for improvement is there?
[−] RockyMcNuts 43d ago
Could be interesting to chart quality of responses, toxicity/health of conversations, sentiment over time, impact of release of ChatGPT.

(since AI can now answer many questions that might have been topics of conversation; people can use AI to participate; people may be reluctant to participate if AI can data mine everything and link it back to them, etc. similar to Stack Overflow)

[−] sd9 43d ago
I'm kind of surprised that postgres was quite that dominated by mongodb back in the day. I remember the mongo fever, but I always thought postgres held reasonable market share. I guess it was other SQL dbs back then, I guess MySQL was still viable.
[−] tombert 43d ago
It could be that Postgres was so popular that people didn't really discuss it.

Hyperbolic example; literally every human reading this consumes oxygen nearly every moment of the day, and as such no one talks about how great breathing is.

[−] hsuduebc2 43d ago
I worked on many projects that had used wrongly mongo instead of ordinary relation database and they needed rework in time. It was just hyped in it's days. Like micro service architecture in few years.
[−] voidUpdate 43d ago
When searching for references to Go, what does it actually look for? "Go" is a relatively common word, and I hardly see anyone referring to it as Golang
[−] hakrgrl 43d ago
That last chart showing the average comment length shows a clear negative downtrend, especially in recent months. I wonder why that is.
[−] hsuduebc2 43d ago
I really love codex. The price/value comparison to claude code is at least from my opinion much better.
[−] moralestapia 43d ago
Do not estimate/plot DAUs/MAUs, it's not a pretty picture :'(.
[−] throwaway290 43d ago
HN data is open? Under what conditions it's distributed?
[−] xnorswap 43d ago
5% of all comments mention Claude code?

Am I reading that right?

[−] sam-bee 43d ago
Nobody who actually codes in that language ever calls it 'Golang'
[−] avib99 43d ago
[dead]
[−] benreesman 43d ago
[dead]
[−] huflungdung 43d ago
[dead]
[−] cloudpeaklabs 43d ago
[flagged]