Hello World,
It's been a while since my last newsletter, and in that time, the world of AI has evolved tremendously. There's been a lot of progress, and I’ve been keeping busy working on several projects with clients as we gear up for awards season.
Despite the hectic schedule, I’ve stayed active in the AI space, integrating new tools into my workflow. Three standout tools I’ve been using and loving are Google’s NotebookLM, ChatGPT-4's Canvas, Bolt AI Coding assistance. I’ve included some project samples below, along with details on how I’ve been using these tools and their specific use cases.
Additionally, I’ve started exploring Meta AI Labs and have been experimenting with Audiobox—it's been a lot of fun. I’m also diving into the latest updates from Fal.ai, which has now become a suite of tools, branded as the generative media platform for developers.
Google NotebookLM was announcement on around September 11th, the new Audio Overview feature can turn documents, slides, charts and more into engaging discussions with one click.
Google Team note:
We built NotebookLM to help you make sense of complex information. When you upload your sources, it instantly becomes an expert, grounding its responses in your material with citations and relevant quotes. And since it’s your notebook, your personal data is never used to train NotebookLM.
A new way to turn your documents into engaging audio discussions. With one click, two AI hosts start up a lively “deep dive” discussion based on your sources. They summarize your material, make connections between topics, and banter back and forth. You can even download the conversation and take it on the go.
It’s important to remember that these generated discussions are not a comprehensive or objective view of a topic, but simply a reflection of the sources that you’ve uploaded.
I recently tried using Notebook ML to analyze a PDF file titled Reshape (Report Vol. 2): Unleashing the Power of Prompt Engineering. After uploading the report to the notebook, I could prompt questions, and the AI responded based on the contents of the PDF. The interface displayed the PDF on the left, acting as a source guide, while the AI-generated answers appeared on the right. Additionally, I had the option to receive an audio summary based on the input content. Listen to the conversational audio overview file below for a high-level overview of the Reshape paper audio.
PDF with Notebook Prompt Interface.
Reshape vol2. notebook audio overview
Chat GTP 4o canvas: A new way of working with ChatGPT to write and code
I tested the new Chat GPT-4o Canvas, a product from OpenAI that allows you to write code for digital applications. I prompted Chat GPT-4o to build a front-end interface featuring an interactive 3D map with anchor points, pinpointing various locations in the South, West, East, and North. Each pinpoint was made clickable, providing additional information and links to details about each location. ChatGPT generated the HTML, CSS, and JavaScript using Three.js and WebGL to render the map. This serves as a baseline code for building websites, and if you're unsure where to start, this tool can assist with writing, testing, and debugging code. As long as you have a basic understanding of HTML and an idea of your digital product's functionality, you can use ChatGPT Canvas and Claude AI to plan and roadmap your website or application.
Codes breakdown
Claude AI -Artifacts
This was one of the first releases from a few months ago. Claude Artifacts is interactive and editable outputs generated by Claude AI in response to user requests.
Bolt.new
It's the most advanced AI-powered code assistance tool, offering intuitive file breakdowns that make it easy to understand and integrate with GitHub. This tool can build complex digital products, and I'm excited to explore it further to see how we can elevate the our projects codebase to the next level.
more to come, currently trying the Meta Lab Audiobox on closed Beta.
In the News: Runway Partners with Lionsgate
Runway and Lionsgate are partnering to explore the use of AI in film production.
Lionsgate and Runway have entered into a first-of-its-kind partnership centered around the creation and training of a new AI model, customized on Lionsgate’s proprietary catalog. Fundamentally designed to help Lionsgate Studios, its filmmakers, directors and other creative talent augment their work, the model generates cinematic video that can be further iterated using Runway’s suite of controllable tools.
“Runway is a visionary, best-in-class partner who will help us utilize AI to develop cutting edge, capital efficient content creation opportunities,” said Lionsgate Vice Chair Michael Burns. “Several of our filmmakers are already excited about its potential applications to their pre-production and post-production process. We view AI as a great tool for augmenting, enhancing and supplementing our current operations.”
Less ego, more Impact!
Share this post