Todd Walters Blog

According to the Farmers’ Almanac, the phrase originated in ancient Roman times. The Romans noticed that the star they called Sirius, the Dog Star, was in conjunction with the sun in late July. They believed the Dog Star’s brightness made things hotter on Earth during the late summer months. So, they named this period diēs caniculārēs, or “days of the dog star,” which was later shortened to “dog days." - As quoted from Saturday 17-Aug-2024 Morning Brew Newsletter, who apparently got it from the Farmers’ Almanac

[Read More]

Just a whole lotta links this time around. Didn’t have a chance to really dig into any of them to provide any kind of commentary or thoughts or opinions. Some good state-of-ai think pieces here, a handful of potential learning projects and some AWS cloud related articles this time around, that I definately want to dig into some more.

Table of Contents

• AI and Machine Learning
  • Preliminary Notes on the Delvish Dialect, by Bruce Sterling | by Bruce Sterling | Jul, 2024 | Medium
  • us-state-of-gen-ai-report-q2
  • FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision | Tri Dao
  • The AI summer — Benedict Evans
  • AI Conundrums – tecosystems
  • Prompt engineering techniques and best practices: Learn by doing with Anthropic’s Claude 3 on Amazon Bedrock | AWS Machine Learning Blog
  • Superintelligence—10 years later - by Conrad Gray
  • [2402.14905] MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
  • 2406.17711v1
  • Linear Algebra Concepts Every Data Scientist Should Know | by Benedict Neo | bitgrit Data Science Publication | Jun, 2024 | Medium
  • Multi AI Agent Systems 101. Automating Routine Tasks in Data Source… | by Mariya Mansurova | Jun, 2024 | Towards Data Science
  • How To Run Llama 3 In Visual Studio Code — A Step-By-Step Guide | by Jim Clyde Monge | Generative AI
  • Gradually, then Suddenly: Upon the Threshold
  • GitHub - karpathy/LLM101n: LLM101n: Let’s build a Storyteller
  • Meet Verba 1.0: Run State-of-the-Art RAG Locally with Ollama Integration and Open Source Models - MarkTechPost
• Cloud Computing and Security
  • Strategies for achieving least privilege at scale – Part 2 | AWS Security Blog
  • Strategies for achieving least privilege at scale – Part 1 | AWS Security Blog
  • secured-bastion-host-terraform/README.md at main · aws-samples/secured-bastion-host-terraform · GitHub
  • Access AWS services programmatically using trusted identity propagation | AWS Security Blog
  • bullfrog/README.md at main · bullfrogsec/bullfrog · GitHub
  • aws-whoami-golang/README.md at main · benkehoe/aws-whoami-golang · GitHub
  • Forward Incoming Email to an External Destination | AWS Messaging & Targeting Blog

AI and Machine Learning

Category Tags: #ai, #llm, #machine-learning, #generative-ai, #deep-learning

As in this post was born on the 4th of July. Nothing more than that. Just a dumb title to a silly link post for the holiday. I actually had a chance to read through and have thoughts on some of these articles, there’s that as well. Enjoy.

Table of Contents

• Artificial Intelligence and Machine Learning
  • The Five Stages Of AI Grief - NOEMA
  • RouteLLM: An Open-Source Framework for Cost-Effective LLM Routing | LMSYS Org
  • AI Patterns – tecosystems
• Development and Programming
  • Meet Verba 1.0: Run State-of-the-Art RAG Locally with Ollama Integration and Open Source Models - MarkTechPost
  • GPT4All
  • Using Generative AI to Create Runnable Markdown | Docker
  • GitHub - posit-dev/positron: Positron, a next-generation data science IDE
  • GitHub - squaredtechnologies/thread: AI-Powered Jupyter Notebook built using React
• Cybersecurity and Responsible AI
  • Mitigating Skeleton Key, a new type of generative AI jailbreak technique | Microsoft Security Blog
  • A discussion of discussions on AI bias
• Data Science and Analytics
  • Quill - AI-powered SEC filing platform

Artificial Intelligence and Machine Learning

Category Tags: #ai, #machine-learning, #deep-learning, #nlp, #generative-ai

Wow. So it’s be another long while, since I got around to creating another post. This one is another link list, based what has caught my eye over the last month. Can’t say I have read them all, but good list to come back to as time permits.

Something I did decide to do based on having all of these articles, was to create a python script that would interact with the Omnivore API (the application I use to grab links and content I want to read later) to grab all the articles I have saved and send all of those to openAI to create a summary and suggest some tags. I will eventually create a write-up for that project, but wanted to get this link list out first. Seems to have turned out ok, but many improvements to make.

It’s weekend number two of the Deep Learning Specialization with the Purdue University Post Graduate Program in AI and Machine Learning program that I have been participating since January. This is the seventh and section of the program which won’t wrap up until mid-July with only the Capstone Project left to complete to finish out the program. This week-end was all about Object Detection, Selective Search, Sequential Modeling, Recurrent Neural Networks, Word Embedding, Long Short-Term Memory and Hybrid Modeling.

Welp seems like I failed at actually maintaining this site once I stood it up at the end of the year last year. I did manage to move my resume details into the About Section of this site and retire the resume site that I originally stood up as part of participating in the Cloud Resume Challenge. Outside of that update things have been totally stagnate here.

I have decided to at least start capturing the articles I have come across that have interested me and any thoughts that come to mind reflecting on the content of the articles. I tried to break these articles up into various categories, but actually they all could fit into every one of these categories.

Are you bored of the same old Christmas traditions? Do you want to spice up your holiday season with some geeky fun? If so, you might want to try learning about Hugo and creating and deploying your first Hugo site to GitHub Pages!

In this blog post, I will show you how to set up Hugo on your computer, create a new site, add some content, and deploy it to GitHub Pages. It’s easier than you think and you’ll have a lot of fun along the way. Let’s get started!