Geek
In my last post, Where have all the Engineers gone?, I wrestled with some tough questions we're facing today, in the age of AI-powered engineering. I can't just leave it there... Just as the rise of automation and CI/CD pipelines reshaped operations teams by forcing traditional sysadmins to upskill into DevOps engineers or risk obsolescence, we’re... Continue Reading →
I grabbed my morning coffee and dove into Apple’s new paper, The Illusion of Thinking (okay fine, ChatGPT and I dove into it together). And you know what? None of this really surprised me. I've been working through creating custom "thinking" agents, leveraging reasoning models. The head-shaped-hole on my desk tells you how well it's... Continue Reading →
Photo by Mike van den Bos on Unsplash We've all been there: managing many moving pieces in our heads and then, BLAM, Slack dings, we’ve lost our perfect mental model faster than closing an unsaved file. Working with LLM agents has upped the ante in terms of what we have to keep in context in... Continue Reading →
While digging through a messy codebase, I stumbled upon an amazing little trick using AI agents in my IDE that instantly brought clarity. It was too cool not to share—plus, now I’ll have a handy reference to myself later. AI Agents in your IDE: Cursor and GitHub Copilot I've tested this out using Cursor and... Continue Reading →
I don't know who gets to pick industry buzzwords, abbreviations, and the like, but I'd like to propose h11n for a short form of an AI hallucination. I swear I gave the LLM the right data but it h11n anyway! My prompt is killing me, it keeps h11n on this one question... That's all, let... Continue Reading →
In my other post/notebook, Using GPT Vision in RAG, we use vision to help enrich our content during ingestion, prior to chat. By using vision, we are able to create robust descriptions of our complex slides that contain charts and graphs, and bring some amazing value to our end users. In this post, we're going to... Continue Reading →
This post is created off of a Jupyter notebook in Github, which you can access here. I copied all the content for this blog post. I've adapted this a little to read easier and include no code, just the good tid bits. We're going to explore using OpenAI's GPT Vision with 4o model to gather... Continue Reading →
Above image created by GPT 4o: Create an image for my blog post. I talk about people using AI and ChatGPT. Create the image photo realistic, and make it look like it’s from the 1930s Brooklyn This guest post is written by my good friend and colleague Karl Schwirz, Director at Slalom, master of AWS, and... Continue Reading →
Just a week ago, OpenAI released o1, their new reasoning model! Have you tried it? I've played around with it and was having a hard time coming up with something to ask it to see its power. I found something that I was really impressed with. Before I get there, what is this thing called... Continue Reading →
OpenAI released ChatGPT-4o, boasting speed, affordability, and intelligence. Before migrating, consider how the new model affects code, features, and limits, such as token count and response limits.
David Lozzi 