Scientists have figured out how to turn TikToks into genetic code by teaching AI to "speak" in DNA.
April 16, 2026
Original Paper
From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage
arXiv · 2604.13667
The Takeaway
For a long time, DNA was just the blueprint for life, but now we're using it as a hard drive—except it’s been notoriously hard to store video data because computer code and genetic code are so different. A new AI called HELIX bridges this gap by mapping video "tokens" directly onto the ATCG alphabet of DNA. Instead of just translating 1s and 0s, it treats DNA like a native language for video compression. This means we could potentially store the entire internet’s worth of video in a single room full of vials. It’s the ultimate backup for human history that won't degrade for thousands of years.
From the abstract
DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low maintenance cost. Over the past decade, substantial progress has been made in storing text, images, and files in DNA -- yet video remains an open challenge. The difficulty is not merely technical: effective video DNA storage requires co-designing compression and molecular encoding from the ground up, a challenge that sits at the intersection of t