←back to thread

Ask HN: What are you working on (August 2024)?

634 points david927 | 5 comments | 24 Aug 24 22:00 UTC | HN request time: 1.194s | source

What are you working on? Any new ideas that you're thinking about?
Show context
kaspermarstal ◴[25 Aug 24 05:45 UTC] No.41344727[source]▶
I am building an Excel extension that lets me use LLMs in formulas. For example, I can write =PROMPT(A1:E1, "Extract keywords") in a cell to extract keywords from a row and drag the cell to apply the prompt to many other rows. I find this useful when I want to use AI for repetitive tasks that would normally require copy-pasting data in and out of a chat window many times.

I actually built it for my girlfriend who was writing a systematic review paper. She had to compare 7.500 papers against inclusion and exclusion criterias. She obviously did this manually because she cares about scientific integrity, but it sparked the idea to make an AI tool to automate repetitive tasks for people like her who would rather avoid programming. Now I just find it useful myself for a lot of ad-hoc analysis tasks like prompt engineering, rag tuning, and comparing model outputs from anthropic, openai, and google.

replies(2): >>41345507 #>>41348400 #
1. mft_ ◴[25 Aug 24 16:10 UTC] No.41348400[source]▶
Huh, I was googling for this exact tool a couple of weeks ago.

Is there anything you can share - about how you're approaching it, and your progress? Need any beta testers? :)

replies(2): >>41349592 #>>41357914 #
2. kaspermarstal ◴[25 Aug 24 18:03 UTC] No.41349592[source]▶
Yes I am really interested in good use-cases, send me an e-mail at kaspermarstal@gmail.com! It’s called Cellm, implemented with ExcelDna and is fully functional for Anthropic models. Currently preparing the repo for public release and writing some docs.
3. kaspermarstal ◴[26 Aug 24 15:12 UTC] No.41357914[source]▶
What’s your use case?
replies(1): >>41360272 #
4. mft_ ◴[26 Aug 24 18:39 UTC] No.41360272[source]▶
I work in a scientific field, and I was analysing a large amount of data related to clinical trials. Part of the work required categorising the data fields, and while traditional Excel approaches were helpful, ultimately I had grind through a large number of fields, manually sorting/categorising and Googling details for about half of the entries.

I wondered whether an LLM could be helpful for some of the steps I was taking manually (hence a quick exploration for such a tool) but there didn't seem to be an easy way to test this. (I could have pulled it into Python and tried to automate it that way, but I didn't time/energy on that occasion.)

(Sorry for the slow reply - travel.)

replies(1): >>41384218 #
5. kaspermarstal ◴[28 Aug 24 20:50 UTC] No.41384218{3}[source]▶
Thanks for sharing! If you want to try it out, it will be published to github.com/kaspermarstal/cellm in the coming weeks. Will reply to this thread when it is live.