91 points by cliffly 10 hours ago | 8 comments
nsbk 1 hour ago
Interesting timing, they have recently reached out to my $dayjob. We will be probably be running a workshop on our (massive) dataset with them. I'd like to evaluate the performance of a couple of analytical models we've manually built against whatever this model can do based on some prompts. Exciting times!
dcrimp 41 minutes ago
interesting! Super cool idea to augment software built with traditional DBs

I had some thoughts [1] around a concept similar to this a while ago, although it was much less refined. My thinking was around whether or not we could have a neural net remember a relational database schema, and be able to be queried for facts it knows, and facts it might predict.

This seems like a much more sensical (and actualised) stab at this kinda concept.

[1]: dancrimp.nz/2024/11/01/semantic-db/

tinyoli 7 hours ago
Strange that they do not compare it against TabFN, which is another foundation model for tabular data. (https://github.com/PriorLabs/TabPFN)
simplesort 8 hours ago
Jure Leskovec was my Professor at Stanford a few years back, cool to see he's behind this.

He seemed like a good guy and got the sense that he was destined to do something big

stuartjohnson12 5 hours ago
Vid is a good friend of mine and he's wicked smart and also a very solid guy I adore.

I'm also guessing at some point he will probably read this comment, so hey Vid! See you at the next VRSA meetup!

andraz 1 hour ago
Wickedly smart team indeed!
SubiculumCode 2 hours ago
So suppose I've got a database of behavioral and neuroimaging data from a research study on autism. Is this something that can be used to predict diagnosis from the other data fields?
bookworm123 7 hours ago
I feel like this is the next big thing for AI, having the ability to interact with any sort of structured dataset out of the box. Very cool project!
perbu 6 hours ago
I'll suspect it'll be more like the next little thing. Most of don't interact that much with structured data, so the applications will be very specific.

However, the algo-trading crowd, will likely be very interested in this. They deal with structured data all day and it would surprise me if most of them don't already have things like this working in their networks. They seem to be very secretive, though, so we're not gonna hear much.

cliffly 4 hours ago
We all interact with structured data models constantly, like literally thousands of times each day, just indirectly.

Every single credit card purchase gets classified by a model as fraud or ok. When you go to Netflix and see recommended movies, it's all predictions on structured data. Every single post in every social media feed is there because a model predicted you'd like it.

Realistically, it might be more like 10s of thousands or even hundreds of thousands of predictions that we engage with in a day.

If reality matches the benchmarks for this model, it can kick off a whole new category of models that can potentially be bigger than LLMs

gk1 4 hours ago
Structured data = relational data

This has more applications than you might first think.

hbarka 4 hours ago
Does AI for relational data work the same way as token predictions does for LLM AI?
EGreg 2 hours ago
So can this be used to predict patterns for traffic, restaurant table availability, and your customers’ demand for things based on other customers?
Rohitcss 8 hours ago
A real-time in-context label generator. Nice...