AI in 10
The most important AI story—explained in 10 minutes.
Every day, I break down the biggest AI story in just 10 minutes - what it is, why it matters, and how you can actually use it. No tech jargon, just AI made simple.
AI in 10
How MIT's AI Designs Cancer Drugs in Hours Instead of Years
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
Referenced Links:
MIT Jameel Clinic GitHub Repository
ClinicalTrials.gov - Track New Trials
Coursera AI for Medicine Course
MIT Official Website
Foldit Citizen Science Game
Want to go deeper with AI? A community of professionals is learning AI together right now at aihammock.com — show notes, links, tools, and real conversations about how to actually use AI in your life.
Welcome to AI in 10. I'm Chuck Getchell, and every day I break down the biggest AI story in just 10 minutes. What it is, why it matters, and how you can actually use it. Picture this, you need a new drug for your cancer. And instead of waiting 15 years for scientists to stumble onto the right combination, an AI designs it in 15 minutes. That's exactly what just happened at MIT. And it's not science fiction anymore. Researchers there just unveiled a generative AI model that doesn't just predict how proteins work, it actually designs brand new proteins from scratch. Think of it as ChatGPT for molecular biology. Except instead of writing your emails, it's writing the code for custom medicines. Here's what makes this a game changer. Traditional drug discovery is basically expensive guesswork. Companies spend 10 to 15 years and up to$3 billion testing thousands of combinations in lab after lab, hoping something works. It's like trying to write a symphony by randomly banging piano keys until something sounds good. But this MIT system flips that entire process upside down. You tell it what disease you want to target, let's say a specific type of brain cancer, and it generates thousands of custom protein designs in just hours, each one tailored to attack that exact cancer while leaving healthy cells completely alone. The technical breakthrough here is solving what scientists call the inverse folding problem. Most AI can look at a protein and predict its shape, kind of like looking at a blueprint and imagining the finished building. But this system does the opposite. You describe the building you want and it creates the blueprint. Professor Regina Barzalay from MIT put it perfectly. This isn't just prediction, it's creation. We're programming biology-like software. And the early results are stunning. The system hit 85% accuracy on protein folding predictions, beating existing benchmarks by 30 to 40%. Now let me connect this to your actual life. Because this isn't just lab news. If you or someone you love has ever waited for a treatment that doesn't exist yet, this changes everything. Cancer patients could get personalized protein therapies in three to five years instead of 10 or more. Imagine getting a treatment designed specifically for your tumor instead of the one size fits all approach we use today. This is especially huge for rare diseases. Right now, about 30 million Americans have genetic disorders that big pharma basically ignores. The market's too small, the research too expensive, so families just wait and hope. But when you can design treatments in days instead of decades, suddenly those orphan diseases become viable. Costs could drop by 50%, making life-saving therapies accessible to regular families. And here's something most people haven't thought about yet. This makes us incredibly prepared for the next pandemic. Remember how long it took to get COVID treatments? With this system, we could have custom antivirals designed and tested within weeks of identifying a new virus, no more years-long waits while people suffer. The really interesting part is how this democratizes drug discovery. The MIT team made their model open source, which means smaller labs, rural clinics, even developing countries can now design their own treatments. You don't need a billion-dollar research facility anymore, just a decent computer and an internet connection. It's like going from needing a printing press to publish a book to being able to self-publish on your laptop. But here's what I find most exciting as someone who's built AI-powered businesses. This isn't just about making existing processes faster. This creates entirely new possibilities. We're talking about programmable biology, where designing a new medicine becomes as routine as writing software. So, what can you actually do with this information today? Let me give you some concrete steps. First, if you're curious about the science, you can actually try this yourself. The MIT team published their model on GitHub. Search for MIT Protein Design Gen AI March 2026, and you'll find notebooks you can run in Google Colab for free. You can input a disease target like a specific cancer protein and watch the AI generate custom protein designs in real time. You don't need to be a scientist to play with it, just a Google account and some curiosity. Second, if you have a health condition that affects you or your family, start following clinical trials. Go to clinicaltrials.gov and set up alerts for MIT generative protein drug or whatever your specific condition is. The first human trials using this technology could start as early as late this year. Being informed means being ready to participate or advocate when opportunities arise. Third, think about your career. This wave of bioAI is creating entirely new job categories. You don't need a PhD in biochemistry anymore to contribute to drug discovery. Coursera just updated their AI for medicine course with modules specifically covering this breakthrough. Customer service reps are becoming patient advocates. Project managers are coordinating AI human research teams, and marketing professionals are explaining complex treatments to families who never had options before. Fourth, if you're entrepreneurial, pay attention to the ripple effects. This technology doesn't just change pharmaceuticals, it changes everything downstream. Medical device companies, diagnostic labs, even insurance companies will need new approaches when personalized protein therapies become routine. There are business opportunities everywhere you look, and here's something practical you can do right now. Start building your health data literacy. When personalized medicine becomes the norm, the people who understand their own genetic profiles, family medical histories, and can communicate effectively with AI-assisted doctors will get better care faster. As I always say, I'm not a doctor or medical advisor. Always talk to a professional for your specific health situation. But I am someone who's spent years watching AI transform industries, and this feels like one of those watershed moments. The experts are calling this the shift from AI hype to AI execution. Andrew Eng said it perfectly last week. BioAI like this moves from promise to practice. Expect protein drugs to flood the pipeline faster than mRNA vaccines did after COVID. Daphne Coller from Incitro predicts this could deliver 10 times more therapies by 2030, especially for underserved diseases that currently get ignored. But here's what really gets me excited about this story. It's not about replacing human creativity or intuition, it's about giving human researchers superpowers. A scientist who used to test 50 protein combinations per year can now test 50,000. That's not artificial intelligence taking over. That's artificial intelligence amplifying human intelligence. And that's the pattern I keep seeing in 2026. The AI that matters isn't the flashy stuff that makes headlines. It's the AI that makes smart people 10 times more effective at solving real problems. This MIT breakthrough matters because it takes one of humanity's biggest challenges, curing disease, and makes it exponentially more solvable. Your kids might grow up in a world where rare genetic disorders are routinely curable, where cancer becomes a manageable chronic condition, and where pandemic responses happen in weeks instead of years. The future of medicine just shifted from reactive to creative, from waiting for cures to designing them on demand. And the best part, you don't have to wait for some corporation to decide if your disease is profitable enough to research. The tools are becoming democratized, the barriers are falling, and the pace of progress is accelerating beyond anything we've seen before. That's today's AI Inten. If you want to go deeper and learn AI with a community of people just like you, join us at aihammock.com. I'll see you tomorrow, my friends.
