Tiny magnetic vortices could help computers work more like your brain
Scientists have filmed tiny magnetic vortices called skyrmions melting out of an organized lattice for the first time, revealing new ways to manipulate these unusual structures. The breakthrough could help make brain-like computers a reality, potentially enabling dramatically smaller and more energy...
Scientists overcome a hidden obstacle to more powerful quantum computers
Scientists have discovered a way to operate multiple silicon qubits simultaneously with remarkable accuracy, overcoming a major challenge in scaling up quantum computers. Their new technique maintained accuracy of approximately 99.9% even when all five qubits were running at once, opening the door t...
47 experiments, zero humans, one night: How I let AI improve my AI skills
There's a slide I open with that always gets people curious. It reads: 47 experiments. Zero humans. One night. People assume it's a movie tagline. It's not...
Solving a 31-year-old grand challenge in mathematics – the KLS conjecture
For decades, a fundamental question about the difficulty of computing in high-dimensional spaces has resisted proof. New research resolves this question, removing a major theoretical obstacle to understanding the efficiency of randomized algorithms used across science and computing. The Kannan–Lovás...
In my work with G7–G12 students at Force Academy, a research initiative in Chongqing, I sometimes take a project that appears to be finished and give another student responsibility for using, checking, or modifying it. The handoff is a test of understanding: Can the work still make sense when its cr...
Prompt rules couldn’t stop a phone agent from confirming messages it never sent. Emre Benian makes the case for letting the model propose and a workflow act, backed by test results from moving dates, identity checks, and receipts into code.
In my previous article, I argued that agentic development needs enough specification to make correctness checkable. A quick prompt can get implementation started quickly, but someone still has to decide whether the result does what we wanted. I left a fairly practical question unanswered, though. On...
Proof-based general-purpose computing with Magnetar
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security.
The post Proof-based general-purpose computing ...
I use AI for writing all the time. But not because it’s good at writing. In fact, just the opposite is true. AI is so reliably bad at writing that I’ve actually taken advantage of that, and made its bad writing an integral part of my writing process. I’ve written a lot of books and […]
Scientists recreate a bizarre quantum effect that stops a particle cold
Oxford physicists have recreated a bizarre quantum effect in which a particle responds to a magnetic field without ever traveling through it. Using a hybrid quantum computer, they demonstrated how introducing a simulated magnetic flux could completely halt a particle's movement through quantum inter...
Physicists discover “astonishing” property of light that defies expectations
Scientists have uncovered a surprising hidden ability of light that allows it to develop spinning, twisting behavior as it travels through empty space, without special lenses, mirrors, or materials. Researchers discovered that light’s internal geometry can naturally produce left- and right-handed pa...
Why enterprise agentic AI needs an evidence standard.
Usage metrics show who logged in. Neetu Yadav sets out a five-part evidence standard covering reach, depth of use, quality, risk, and business impact, so enterprise leaders can scale agentic AI with confidence.
On a recent episode of This Week in AI, we discussed that the number of nonhumans on the internet is greater than humans, 144 to 1. It’s an estimate, and the order of magnitude is more important than the number itself. What matters is what a ratio anywhere in that range does to a security […]
Renting GPUs felt smart in 2023. The math has moved
Many enterprise AI initiatives started the same way over the past several years: renting cloud capacity, running pilots, and scaling successful projects. That approach made sense when nobody knew if these use cases would actually hold up in a live production environment...
The Preservation Gap in the AI Stack: Why Capability Is Advancing Faster Than Reconstructability
Artificial intelligence systems are difficult to reproduce because their behavior depends on nondeterministic models and on data, configurations, policies, and external services that continue to change. But exact reproducibility is not always what operators, investigators, or auditors need. They oft...
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.
The post What AI gets wrong and wh...
How to Build Reliable AI Agent Systems for Production
The following article was originally published on the Agentic AI Foundation blog site and is being republished here with the author’s permission. A customer asks your company’s AI agent to update the shipping address on account 123. The agent relies on a support ticket with a typo and updates accoun...