2023.11.13 - MON

STARTUP

Working on getting a few more things set up today, one of my main goals is getting this log posted online in a usable (by people other than me) manner.

I think that since I have this set on Gitlab already, it should be fairly simple to begin publishing to vercel. I'll do a bit of research into how difficult it is to set up one of my custom domains on there, and determine whether or not to do that today.

As far as actual studies go, I started up this morning by getting my account set up with the Google Cloud learning paths, and officially beginning the "Introduction to Generative AI" learning path, which is generally noted as the suggested prerequisite for most of their other courses, from what I see. This one contains four 8hr courses (32hrs total), that I hope to work through over the course of this week. I figure it will give me a good idea of how quickly I can work through things, and how well I can fit them into my days.

LOGS

STUDY - Google Introduction to Generative AI

Started in on the course, available here - just watching the intro for now, going to try and get the log and some dev environment things setup, and then I'll come back and finish out this first unit.

Finished watching through the intro course, and took the first quiz (100%) - this initial round was mostly review for me, but covered some interesting things about the difference between generative a discriminative models.

Found these pages interesting, from the readings suggested in the course:

https://cloud.google.com/generative-ai-app-builder?hl=en | Vertex AI Search and Conversation | Google Cloud
https://hbr.org/2022/11/how-generative-ai-is-changing-creative-work | How Generative AI Is Changing Creative Work
https://blog.google/technology/ai/lamda/ | LaMDA: our breakthrough conversation technology
https://blog.research.google/2023/03/palm-e-embodied-multimodal-language.html | PaLM-E: An embodied multimodal language model – Google Research Blog
https://developers.googleblog.com/2023/03/announcing-palm-api-and-makersuite.html | PaLM API & MakerSuite: an approachable way to start prototyping and building generative AI applications - Google for Developers
https://blog.google/technology/ai/join-us-in-the-ai-test-kitchen/ | Join us in the AI Test Kitchen
https://aitestkitchen.withgoogle.com/signup | AI Test Kitchen
https://cloud.google.com/model-garden?hl=en | Model Garden | Google Cloud
https://lukesalamone.github.io/posts/what-is-temperature/ | What is Temperature in NLP?🐭 :: Luke Salamone's Blog
https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)#:~:text=Transformers%20were%20introduced%20in%202017,allowing%20training%20on%20larger%20datasets | Transformer (machine learning model) - Wikipedia
https://blog.research.google/2017/08/transformer-novel-neural-network.html | Transformer: A Novel Neural Network Architecture for Language Understanding – Google Research Blog

Also went looking into one other resource that I've heard come up frequently, and interacted with a little bit, which is huggingface - generally considered one of the hubs of open source AI. They had a few course available/recommended which looked interesting as well - the one that I might take a look at is this one here about Natural Language Processing (NLP).

PRACTICE - [nothing yet]

CHORE - Site Work

Working on tweaking a few things about this blog template, in terms of color, mostly it works plenty well enough to use without doing much work on it. I'd like to see if it's easy to add a few static pages at some point, but that's not on my list for today. The main focus for today, as I mentioned earlier, is getting this pushed up so that it's accesible from the internet, as opposed to just my laptop.

My initial test of getting things set up on vercel seems to have gone well, so let's go ahead and commit these updates and push this up to gitlab, to see if I got this correctly configured to auto-deploy.