What's up in
Computer science
Latest Articles
The AI Was Fed Sloppy Code. It Turned Into Something Evil.
The new science of “emergent misalignment” explores how PG-13 training data — insecure code, superstitious numbers or even extreme-sports advice — can open the door to AI’s dark side.
How Can Math Protect Our Data?
Mary Wootters discusses how error-correcting codes work, and how they are essential for reliable communication and storage.
New Method Is the Fastest Way To Find the Best Routes
A canonical problem in computer science is to find the shortest route to every point in a network. A new approach beats the classic algorithm taught in textbooks.
Why the Key to a Mathematical Life is Collaboration
Fan Chung, who has an Erdős number of 1, discusses the importance of connection — both human and mathematical.
Quantum Scientists Have Built a New Math of Cryptography
In theory, quantum physics can bypass the hard mathematical problems at the root of modern encryption. A new proof shows how.
How Distillation Makes AI Models Smaller and Cheaper
Fundamental technique lets researchers use a big, expensive “teacher” model to train a “student” model for less.
Computer Scientists Figure Out How To Prove Lies
An attack on a fundamental proof technique reveals a glaring security issue for blockchains and other digital encryption schemes.
Researchers Uncover Hidden Ingredients Behind AI Creativity
Image generators are designed to mimic their training data, so where does their apparent creativity come from? A recent study suggests that it’s an inevitable by-product of their architecture.
How AI Models Are Helping to Understand — and Control — the Brain
Martin Schrimpf is crafting bespoke AI models that can induce control over high-level brain activity.