Live data from Hacker News

Spreadsheets are all you need

spreadsheets-are-all-you-need.ai

171–178 of 178 posts

Re: Spreadsheets are all you need

#171
post #18

Creator here. Thanks for posting this! Happy to answer questions or take suggestions and hope it helps folks better understand LLMs. Next video will be on embeddings and hopefully done soon-ish.

moovweb mafia strikes again

Hopefully this outlasts the harlem shake bookmarklet...

Re: Spreadsheets are all you need

#172

Earlier quoted context omitted.

Why?

To be notified of updates. Why in preference to email? Web feeds are typically presented as information streams while email is presented as interpersonal dialogue. Organizing your information streams into an aggregator is clarifying.

Thank you

Re: Spreadsheets are all you need

#173

Earlier quoted context omitted.

Why?

> Why? Cannot answer for parent post, but can share personal perspective. I love Atom / RSS because it allows me to aggregate all the information that I care about in one place. It greatly improves the signal to noise ratio and spares my communication channels for direct human interactions.

Thanks!

Re: Spreadsheets are all you need

#174
post #53

Spreadsheet link https://github.com/ianand/spreadsheets-are-all-you-need/rele...

I'm not a big Excel user, but I see errors that I get when I type in English function names while using a non-English version of Excel. Is it correct that functions (and thus this xlsb file) are not portable to other language versions of Excel?

They are portable, but the displayed function names are translated depending on the local. Same as comma vs dots.

Re: Spreadsheets are all you need

#175
post #18

Creator here. Thanks for posting this! Happy to answer questions or take suggestions and hope it helps folks better understand LLMs. Next video will be on embeddings and hopefully done soon-ish.

This work is another classic in the "neural nets meet spreadsheets" genre [0]. Really helps visualize what is going on in (at least some) latent spaces. [0] https://vusd.github.io/spacesheet/

This is so awesome!! I'm going to have to show this in the embeddings video I'm working on when I discuss non-text embeddings and CLIP.

While I created spreadsheet-are-all-you-need.ai as teaching tool, as I've been playing with it I've been having a growing suspicion the spreadsheet interface for AI might be useful beyond teaching, either as a power user control interface or for interpretability. For example, making simple changes to the architecture of GPT and observing how it changes the model behavior can be as simple as cloning a tab and a few spreadsheet functions. Of course, you can do the same in python as well so it remains to be seen.

A HUGE THANKS!

Re: Spreadsheets are all you need

#176
post #175

Earlier quoted context omitted.

This work is another classic in the "neural nets meet spreadsheets" genre [0]. Really helps visualize what is going on in (at least some) latent spaces. [0] https://vusd.github.io/spacesheet/

This is so awesome!! I'm going to have to show this in the embeddings video I'm working on when I discuss non-text embeddings and CLIP. While I created spreadsheet-are-all-you-need.ai as teaching tool, as I've been playing with it I've been having a growing suspicion the spreadsheet interface for AI might be useful beyond teaching, either as a power user control interface or for interpretability. For example, making…

Excel is getting Python “embedded” soon. Might make some of this easier.

Re: Spreadsheets are all you need

#177
post #175

Earlier quoted context omitted.

This is so awesome!! I'm going to have to show this in the embeddings video I'm working on when I discuss non-text embeddings and CLIP. While I created spreadsheet-are-all-you-need.ai as teaching tool, as I've been playing with it I've been having a growing suspicion the spreadsheet interface for AI might be useful beyond teaching, either as a power user control interface or for interpretability. For example, making…

Excel is getting Python “embedded” soon. Might make some of this easier.

It's actually available in beta. It was announced while I working on this project but I kept going with pure Excel functions because I wanted to illustrate the transformer without abstractions getting in the way. It would make many aspects easier but also make it easier to hide a lot.

That being said, Python+Excel makes a ton of sense in general. And in this project, it would help in the tutorials. For example, in the embeddings tutorial I'm working on I wanted use PCA plots and SVD to illustrate the workings of embeddings but neither are natively supported in Excel without paid plug-ins. But both are easy in Python.

Post reply on HN