Large Language Models Asserting Themselves

Wow!  My last post on this blog was on July 26, 2020.  It was four years and 14 days ago, prior to President Joe Biden being elected, hoards of disgruntled individuals storming the US Capitol, and ChatGPT asserting itself on the technology world.  

What is ChatGPT?  It's OpenAI's chatbot.  It is based on artificial intelligence, specifically Large Language Models (LLM).  If you ask ChatGPT, "Can you write me a blog entry about ChatGPT and "LM?" it gives me the following answer: "Certainly! Here’s a blog entry about ChatGPT and Large Language Models (LLMs).” Assuming you clicked on the link,  you can see it did my work for you.  Initially, it was great, but the more I played around with it, I realized that, like any other technology,  it has its benefits and drawbacks.

It's great for prototyping and brainstorming.  I, however, would not put merit into developing new products with the appropriate quality measures.  For instance, I created outlines for strategy documents, but the selection and sequencing of the document sections were based on what I was trying to communicate to the audience.  Recently, I began developing a board game for kids, and I wanted to create a quick prototype on the web using ReactJS.  The prototype is to refine the gameplay, and I didn't spend a lot of time architecting the ReactJS application.  Still, I realized that it wasn't easy to customize ChatGPT-generated code. I didn't have a good grasp of the ReactJS fundamentals.  I, therefore, decided to take a brief pause and focus on the fundamentals, including the syntax.  A few days ago, I got selected to be an AI tester for Outlier.ai.  It's fascinating how the backend works, and products like ChatGPT, Google Gemini, and others need refinement.  Since I was introduced to cybersecurity at work around the time of my previous blog post, I am interested in seeing how the cybersecurity landscape will evolve LLMs.   Black hat hackers and other "baddies" are the creative ones since they are constantly exploiting technologies to make a profit.  I am specifically interested in how data, cyber, and IT systems intersect without impacting user experience and optimizing business.