Collaborative Calculation and Data Science

colby

sagemath

cornellcollege

facebook

github

google

depaul

We released another round of large language model updates. You can now use [GPT-4o Omni](https://openai.com/index/hello-gpt-4o/) and [Gemini 1.5 Flash](https://deepmind.google/technologies/gemini/flash/). Both are not only very capable, but also extremely quick with their replies.

Here is an example how I improved a plot of a t-test using R in a Jupyter Notebook. This is a visual check to see, if the data is really significantly different. The plot looks a bit boring, though:

![](https://cocalc.com/share/raw/ec225235f8d347b7849a61cca6d448f30a486f21/published/2024-05-16-t-test.png)

Via **AI Tools** → **Improve**, I can tell GPT-4 Omni to make this a violin plot and more colorful

![](https://cocalc.com/share/raw/ec225235f8d347b7849a61cca6d448f30a486f21/published/2024-05-16-t-test-improve.png) 

I get a response and can review the changes in side-chat. The result looks like that:

![](https://cocalc.com/share/raw/ec225235f8d347b7849a61cca6d448f30a486f21/published/2024-05-16-plot-improved.png)

Much better!

Ok, but wait, what's the T-Test? Here, I'm asking Gemini Flash to explain this to me, and there was also something called shapiro. To learn more, I opened a new chat and asked away. I told Gemini to also show me how to do this in R – which I can run directly in the chat.

![](https://cocalc.com/share/raw/ec225235f8d347b7849a61cca6d448f30a486f21/published/2024-05-16-ttest-chat-gemini-flash.png)


GPT-4o and Gemini 1.5 Flash

Compute Server VPN 

Over a Dozen New Videos

Product

Resources

Company