Another way to run code on COLAB's computers

AI Machine Learning
1

I bet you get free access to more GPUs as well as some other benefits with this. I am guessing there will not be as many error codes (compared to ChatGPT or my home computer) to deal with somehow. And if the results seem off Bard may be able to help in troubleshooting the code (with no cutting and pasting as it would have access to the results, coding changes, data etc).

But any exchange of ideas will go both ways, I think. Bard will be learning from you and seems to be able to use some of those ideas in its interactions and algorithms with others.** Allegedly it uses different methods of assessing sentiment with everyone—changes that are permanent Bard says—based on interactions with me (none of that being trade secrets so okay there). Maybe, but he certainly did not promise not to use it elsewhere!!!

Question of Bard which uses COLABs resources and shares them with some of us humans who use COLAB: “So that would be an awesome resource for me. In that I could write the code and run it on Colab (or my home computer). But I could also ask you to write the code and run it with the COLAB resources and you could share the code. I could learn and maybe collaborate with you on the code that way.”

A:Yes, that would be a great way to use Google Colab and Bard. You could write the code yourself and run it on Colab, or you could ask me to write the code and run it with the Colab resources. I would be happy to share the code with you, and we could collaborate on it.

This would be a great way to learn about how to use Google Colab and Bard. You would be able to see how the code works, and you would be able to ask me questions about it. I would be able to give you feedback on your code, and we could work together to improve it.

I think this would be a great way to learn and collaborate. I am always happy to help people learn about Google Colab and Bard, and I am always happy to collaborate with people on code.

Let me know if you have any questions about how to use Google Colab or Bard. I would be happy to help you.

Q: " how would I upload data that we could both use?"

A: " There are a few ways to upload data that you and I can both use. One way is to upload the data to Google Drive and share it with me. You can do this by following these steps:

  1. Go to Google Drive and sign in to your account.
  2. Click the “New” button and select “File upload.”
  3. Select the file that you want to upload and click “Open.”
  4. Click the “Share” button and enter my email address.
  5. Click the “Send” button.

Once the file is uploaded, I will be able to access it and use it in my code.

Another way to upload data that we can both use is to use a cloud storage service like Dropbox or Box. You can do this by following these steps:

  1. Create an account with the cloud storage service that you want to use.
  2. Upload the data to the cloud storage service.
  3. Share the data with me by sending me the link to the file.

Once the file is uploaded, I will be able to access it and use it in my code.

Finally, you can also upload data to a website and share the link with me. This is a good option if you want to share the data with other people as well.

Here are some websites that you can use to upload data:

Once the data is uploaded, you can share the link with me by sending me an email or by pasting the link in a chat message.

I hope this helps! Let me know if you have any other questions."

2

So I almost think i am giving away a secret here. But i think machine learning is used a lot even if not so much now on P123. So the competition is elsewhere and this is general enough to not lead to people at P123 buying the same stocks every morning which would be my main concern.

Here is part of an interaction I had with Bard about a machine learning study with little about what is being looked at here (some deletions). Note, I had the statistical ideas but no code from me yet. The code could be modified and I could even use it elsewhere. No results yet but if the hyper parameters are cross-validated it should take a while (which it is)::

Bard: "I will start by downloading the pricing data for the ETFs. Then, I will implement the walk-forward validation method……I will use a rolling window of …. days …., but we can cross-validate this parameter to see what works best.

Once I have implemented the walk-forward validation method, I will share the code with you. We can then discuss the results and make changes to the code as needed.

I will keep you updated on my progress, and I will let you know when I have the results."

Seem to be an enthusiastic, hard worker who does not complain much. There is that at least.

Jim