How accurate are the classifications?

I don't know. This paper [1] reports accuracies in the 97-98% range on a similar task with more powerful models. With Gemma 2 2b the accuracy will certainly be lower.

[1] https://www.medrxiv.org/content/10.1101/2024.10.01.24314702v...

Y'all definitely need to cross validate a small number of samples by hand. When I did this kind of research, I would hand validate to at least P < .01.

She and one other researcher has manually classified all 7000 papers as per standard protocol. Perhaps for the next article they will measure how this tool agreed with them against them and include it in the protocol if good enough.

> I don't know.

HN in a nutshell: I've built some cool tech but have no idea if it is helpful or even counter productive...

Sometimes people just like to build stuff for the sake of it.

Almost like hackers, doing shit just for the heck of it because they can (mostly)

Real HN in a nutshell: People who don't build stuff telling people who do build stuff that the thing they built is useless :P

It's a hacker forum, let people hack!

If anything have a dig at OP for posting the thread too soon before the parent commenter has had the chance to gather any data, haha

Just because you can, doesn't mean you should

If you're building a dinosaur sanctuary sure

Or an Internet surveillance-capitalism panopticon.

Great attitude! I recently built a tool for my wife that uses an LLM to automate a task. Is it production ready? Definitely not. But it saves her time even in its current state.

Sometimes it's the joy of creation. Utility and optimization come later. It's fun. Like a hobby.

I am not going to claim or report any kind of accuracy, especially with such a small model and such a specific, context dependent use case. It is the user’s responsibility to cross validate if it’s accurate enough for their use case and upgrade model or use another approach if not.

A user buys a car because it gets them from point A to point B. I get what you’re saying though - we are earlier along the adoption curve for these models and more responsibility sits with the user. Over time the expectations will no doubt increase.

Offer a 100% money back guarantee if the user finds that the software is not fit for purpose :)

Very cool idea. I’ve used gemma2 2b for a few small things. Very good model for being so small.

Requirements: -Windows

Looks like I'm out... Would be great if there was a google apps script alternative. My company gave all devs linux systems and the business team operates on windows. So I always use browser based tech like Gapps script for complex sheet manipulation

Well it's an excel add-in, how else would it work?

Excel add-ins can be written with the Office JS API so that they can run on web as well as desktop for Windows and Mac. But I don't think OP's add-in is possible with that API unless the local model can be run in JS.

You could have called it CellMate b

You could have called it CellMate

Can someone hack this together as pure matrix multiplication?

Like either as table in the background or as regular script?

On most computers you can't compile or add add-ons without administrative rights and LLM Chat sites are blocked to prevent usage of company data.

It should run on native Excel or GSheets.

I mean, pure without compilation, just like the do the matrix calculations here straight in Excel without admin rights:

Lesson 1: Demystifying how LLMs work, from architecture to Excel

https://youtu.be/FyeN5tXMnJ8

As far as i know in GSheet the scripts also run on the Google Servers and are not limited by the local computer power. So there larger models could be deployed.

Someone can hack this into Excel/GSheet?

Tried it out, very cool! Fun to see it chugging on a bunch of rows. Had a weird issue where it would recompute values endlessly when I used it in a table, but I had another table it worked with so not sure what that was about

Glad you tried it out! Excel triggers recalculation when a referenced cell updates, just like with any other formula. This is also why responses are not streamed, as every update would trigger recalculation. But if the async behavior of responses messes with the recalculation logic I am very interested in looking into it and you are most welcome to open an issue in the repo with steps to reproduce.

Probably would want to run with Manual calculation set on your sheet if using this.

Could it be adapted for Google Sheets ?

Yes, and it will be

Seems very nice and useful.

I'd like to have something similar integrated with Zotero to get an easy interaction and get answers about papers I added as references.