February 20, 2026
By: Stephen Toback
AI audio tools keep improving, but every now and then something feels like a real leap forward. The Vocal Isolation feature from ElevenLabs is one of those moments. I ran a series of practical tests — not lab conditions —...
Read the full post »
February 17, 2026
By: Stephen Toback
https://warpwire.duke.edu/w/TToJAA/ OK - this is C- quality, but this is the best I've ever seen. Our dream of video automation is to input some text and see a video when you're done. While we're making great progress for certain parts...
Read the full post »
By: Stephen Toback
As many of you know, I’ve been deep in the trenches of testing AI video creation for academic projects at Duke University. My "litmus test" has always been trying to accurately animate molecular bonding—a project that dates back to the...
Read the full post »
February 16, 2026
By: Stephen Toback
I recently had an experience that shifted my entire perspective on AI support. I wasn’t just "chatting" with a bot; I was collaborating with a high-level developer who happened to have a perfect memory and X-ray vision. I spent three...
Read the full post »
February 13, 2026
By: Stephen Toback
In a previous post, I detailed the struggle of getting AI video models to respect the laws of chemistry. This week, an undergraduate attendee at my seminar on AI and video mentioned he was getting impressive results with Seedance 2.0....
Read the full post »
February 11, 2026
By: Stephen Toback
When you fire up Photoshop in 2026, you aren’t just opening an image editor; you’re entering a hybrid workspace where local processing meets the heavy lifting of the cloud. But as Adobe leans into its "ethical" AI branding, a fascinating...
Read the full post »
February 10, 2026
By: Stephen Toback
On of my colleagues reached out to me today looking to create some animation for their training decks. I'm thinking about some ideas to add animation so I did a quick test for Google Veo 3 in Google Flow. I...
Read the full post »
By: Stephen Toback
Overview and Motivation Over the past several years, I have been testing AI-generated video animation as a potential tool for using video to reinforce learning objectives. The goal of this work has never been to create visually impressive or cinematic...
Read the full post »
By: Stephen Toback
We’ve all seen it: you ask an AI to generate a scientific diagram, and there, buried in the pixels, is a faint, ghostly watermark. Usually, we assume the AI is just mimicking "professional" vibes. But a recent experiment reveals something...
Read the full post »
February 5, 2026
By: Stephen Toback
I wanted to extend that scene that was created in Luma (https://sites.duke.edu/ddmc/2026/02/05/robosteve-more-testing-with-luma-ai/) I used ChatGPT to take a frame of the Luma video and and have it create a "model sheet". This is a common pre-visualization tool that allows a...
Read the full post »
