AI

I will do a little experiment and let ChatGPT also write this blog post. I have made minor edits to ensure it aligns with the screenshots, but this is not me! A few essential items before we dive in: I am using GPT4 with Data Analysis through a paid account I work in the energy space, so I knew basically what I was trying to do with the prompts The Consumers website could have done this analysis in precisely 3 clicks through their portal, so I saved little time Yes, we use a ton of electricity! We have a large geothermal system, 22kw solar array, and 26kw of batteries in the basement. We also have 2 Electric Vehicles and a manufacutring shop on the land. ChatGPT Shortcomings: There is no confidence rating here. You ask the model; it gives answers. Are those answers correct? Sometimes. There is a fallacy that you upload and ask away. In another exercise, I needed to go back and validate the PDF breakout, and the table read needed to be corrected. Verify everything. For a site-by-site analysis, this works great, but scaling this would require API integration. Back to my first point here, you would trust that automation wholeheartedly. As technology advances, the ability to quickly ingest and distil complex tariff documents will be a net positive to the energy industry. We are close, but not there just yet. Steps I used to complete this exercise: I went to GreenButton Connect for Consumers and downloaded my interval and billing data. I tried using some lower-level interval data from my parallel metering, but it was too small of an interval to process correctly. Downloaded the latest tariff book for all Consumers Energy rates. Logged into ChatGPT, selected my GPT4 analysis mode and provided the prompt - How does my utility bill compare to other people in Michigan? before starting to have it evaluate the usage against the tariff specifically. Reviewed the Python code and processing You can see the entire chat minus the actual code here: ChatGPT Chat Prompts ...

Have you ever watched a video and thought, “Is this even real?” In today’s age of digital manipulation, discerning the real from the fake has become an intricate dance. I decided to see how the non-tech folks in my life would react to me using AI and Machine Learning to become multilingual maestro. The Genesis of the Idea The adventure began when I stumbled upon a post on Mastodon about using AI to generate deepfake videos. “Deepfakes,” if you’re unfamiliar, are videos produced through machine learning that often superimpose someone’s face or manipulate their voice to make it look like they’re doing or saying something they haven’t. It’s fascinating, but the implications can be quite worrisome. ...