Engineer on ChatGPT for Excel here. Useful feedback. We have improved the latency inside the add-in a lot and a lot more to come. We also have the Fast, Standard and Heavy thinking modes, where you can adjust the thinking time depending on the task complexity. Curious to hear your feedback once you try this out!

Would love for you to try both copilot and ChatGPT for Excel. Agreed on the limitations - but in our experience, ChatGPT for Excel does really well on complex sheets.

Hi, engineer on this add-in. Fair concern but we never train on any of our business or enterprise user data, or if you have opted-out of training on your ChatGPT account.

Forgive my ignorance. How do you folks manage context retention? Say if someone had a sensitive excel document they wanted inference done over, how is that data actually sent to the model and then stored or deleted?

It seems one of the biggest barriers to people's adoption is concern over data leaving their ecosystem and then not being protected or being retained in some way.

Is this is an SLA that a small or medium sized company could get?

If you're concerned, you don't send it outside of the M365 boundary and presumably your admin has Purview Sensitivity Labels in place covering the document to prevent such activity.

Doesn't that mean you can't actually use it for those sensitive documents?

Correct.

{EDIT} English and or the concept of written word may be foreign to you. Thank you for your assistance.

Not sure why you'd state that. 'Correct' is a grammatically correct and complete sentence to your question.

Yeah, I was expecting that you do not train on business or enterprise user data. However, I am not just worried about "training", but also about "sharing". Furthermore, I am worried about cases where an individual has chosen to integrate an add-in and then inadvertently leaks sensitive data.

However, it may be important to note that these security considerations are relevant for most Office Add-Ins (and not just the ChatGPT add-in).

Hi everyone, engineer on ChatGPT for Excel here - we launched ChatGPT for Excel to bring the power of GPT-5.4 to Excel. Keen to hear feedback and happy to answer any questions!

I've had a spreadsheet integrated with ChatGPT API for a few years already. It really was not until GPT-5.4 that the models were able to actually be useful.

What is the data model that you use for the spreadsheet itself? I found I could create a chat completion persona that believed it is one of the developers of a popular open source spreadsheet, and I put this "agent" directly inside the open source spreadsheet. I did this before tool calling was available at all, so I made my own system for that, and the "tools" are the API of that open source spreadsheet. My agent(s) that operate like this can do anything the spreadsheet can do, including operate the spreadsheet engine from the inside.

What API/approach does it use to edit sheets?

I made a CLI (+skill) so agents could edit files with verbs like `insert A1:A3 '[1,2,3]'`, but did some evals and found it underperformed Anthropic's approach (just write Python).

How well does this work compared with using GPT-5.4 in Nicopreme’s Pi for Excel?

have you got a link to this?

Sorry, I got the author wrong.

It's here: https://github.com/tmustier/pi-for-excel

Do you also have Google Spreadsheets on your radar?

https://www.techinasia.com/ -- they have high quality tech journalism for Asia

This actually had some good focus on Indonesia and SEA in general, which was a pleasant surprise

IMO folks are better off deploying their own version where they can adjust a few knobs (e.g. split chunk size) to get better results, given that PDF Q&A is such a commodity application.

Wrote a <50 lines version with LangChain to run on your terminal with any folder full of PDF documents - https://github.com/angad/dharamshala/blob/main/docs.py

return_source_documents is particularly helpful to get a sense of what is being sent in the prompt.

Consider adding a bit of overlap to the text chunks. Say, 300 tokens:

  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=300)

Otherwise, you'll likely end up with too many edge cases in which only part of a relevant context is retrieved :-)

This is actually pretty insightful - I have done something similar with splitting my obsidian data into chunks using paragraphs and headers as demarcation, but this solves a more interesting problem of nuance! I like it.

If you're interested in improved chunking, I mentioned a few strategies in my talk here (timestamp linked, <1min): https://youtu.be/elNrRU12xRc?t=536 that I used when building https://findsight.ai

If you're already splitting documents by paragraph, consider using (as much as possible of) the previous and next paragraphs as overlap.

We did chunks with a sliding window of previous page + current page + next page, with overlaps. That produced the best results.

This would be much more useful if it used vicuna or you could select a different model

The link to your repo is returning a 404 now, whereas I could see it just a min ago.

Created a pi-hole friendly blocklist https://gist.githubusercontent.com/angad/3db2da1cb50a4432c9e...

Stack Overflow newsletters[1] are great as well. It sends you top questions of the week, both answered and unanswered. Great way to learn small things about things you love. Its the perfect application of "Knowledge should be bite-sized".

I subscribe to RPi, Net Eng, CS, theoretical CS and Code Golf news letters. Any other suggestions?

http://stackexchange.com/newsletters

edit: Added link

It took me 15 minutes to make this. I use my own framework that collects tweets based on hashtags and posts to Tumblr and other social networks. Probably its my way of remembering the man who gave the world the device from which I am typing this.

I bought livelikesteve.com for $7.49 from Godaddy and the ads are there just to get me back that cost. Waiting for DNS propagation.

Cameron Winklevoss Status: Enemy Facebook stake: .022%