TWIL: April 16, 2023

Am I the only one who thinks everything is moving really fast? I’ve been on vacations for a week and so much has happened I haven’t had a chance to catch up yet. I still got to listen to two fantastic episodes of Lex Fridman’s podcast, which I highly recommend. They are both great conversations (even if a little long) on several very interesting topics. I’m also highlighting articles on the security of Azure Open AI Service and how to use it to access data in Azure SQL, Semantic Kernel and AutoGPT, the powerful (and a little scary) autonomous GPT-4 experiment. Enjoy!


Lex Fridman Podcast

Episode 370: Edward Frenkel: Reality is a Paradox – Mathematics, Physics, Truth & Love
Edward Frenkel is a mathematician at UC Berkeley working on the interface of mathematics and quantum physics. He is the author of Love and Math: The Heart of Hidden Reality.

Episode 371: Max Tegmark: The Case for Halting AI Development
Max Tegmark is a physicist and AI researcher at MIT, co-founder of the Future of Life Institute, and author of Life 3.0: Being Human in the Age of Artificial Intelligence.

Azure Open AI Service

Peeling Back the Layers: Understanding the Multi-Faceted Approach to Azure OpenAI Security
One question I often hear is: “How does Azure OpenAI differ from OpenAI?” This is especially important for security teams who want to ensure that appropriate security measures are in place. Their aim is not to impede innovation, but rather to create a safe and trusted environment for innovation. While Microsoft’s documentation provides comprehensive information, it can be helpful to supplement discussions with visual aids, especially for C-level executives who may have limited time and prefer a high-level understanding of the topic to start with.

Make data more human with Azure OpenAI and Azure SQL
In this post, we will see how you can use Azure Open AI models to query your SQL tables. The idea is that of generating SQL queries using Azure OpenAI models’ API with Python code.

Semantic Kernel

Hello, Semantic Kernel!
Artificial intelligence (AI) and Large Language Models (LLM) are helping to transform the way we develop and interact with software. From chatbots to code generators, natural language is the future of user interaction, delivering delightful and intelligent “copilot” experiences. As these AI models become more prevalent and accessible, organizations and developers are looking for ways to quickly and easily integrate these capabilities into applications without needing to train or fine-tune a model from scratch.


Early Lessons From GPT-4: The Schillace Laws
What if you could use natural language to create software? What if you could leverage the power of a large-scale language model that can generate code, data, and text from simple prompts? What if you could balance the trade-offs between leverage and precision, uncertainty and interaction, complexity and simplicity? These are some of the questions that Sam Schillace, a software engineer and entrepreneur, explored when he had early access to GPT-4, the latest version of OpenAI’s generative pre-trained transformer model.

How ChatGPT Could Escape to The Internet ‘For Real This Time’
Byhigh interest and popular demand following the first published attempt of ChatGPT breaking out into the internet, this sequel looks at making it happen “for real this time.” This is what I asked ChatGPT to do, and here is an account of how far we got with it this time.


Auto-GPT: An Autonomous GPT-4 Experiment
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM “thoughts”, to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.

AutoGPT — The next big step in AI — Based on GPT-3.5 and GPT-4 — Almost AGI!
While browsing through the latest AI-news I stumbled upon a new hot topic on github called “AutoGPT”. While I thought this will surely just be another GPT-Plugin or Chrome-Extension, I soon realized that it was a whole lot more.

Have a brilliant week!