Read our blog and carry on

A radiologist on a standard hospital shift may read dozens to well over a hundred imaging studies, depending on subspecialty, setting, shift structure, and case complexity. Each one is a search for something that might be subtle, easy to miss, or buried in noise. At that volume, non-trivial discrepancy or error rate is a known risk in radiology practice, especially under high workload and time pressure. Radiologists are working through growing imaging volumes with a workforce that has never full

AI-powered products can create real value, but only when they continue working reliably in the hands of customers. What makes this difficult is that their behavior doesn’t stay fixed after release. As data changes, so does model performance, which means that quality can decline even when no one touches the code. According to the 2024 DORA report, elite teams typically deploy on demand (multiple times per day), recover from failed deployments in under an hour, and keep change failure rates around

A computer vision model can look perfect during testing and then fall apart the moment it meets real life. The contrast is often dramatic. An MIT review found some face-analysis systems making mistakes on 34.7% of dark-skinned women, while the error rate for light-skinned men stayed under 1%. In agriculture, models that scored 95–99% accuracy on clean lab photos fell to 70–85% on real crops. And in radiology, an RSNA review showed four out of five models performing worse on data from another hos

Coding is changing fast, and AI is now writing much of it. In 2025, more than 15 million developers use copilots like GitHub Copilot, Google Gemini Code Assist, and OpenAI’s coding tools to work faster and with fewer mistakes (GitHub usage data). Surveys show that 9 out of 10 engineering teams rely on AI assistants, with many reporting 25–50% productivity gains. The newest trend is the rise of specialized copilots for speech recognition and computer vision. These tools include built-in knowledge

So many of us have used different Facebook applications to see us aging, turned into rock stars, or applied festive make-up. Such waves of facial transformations are usually accompanied by warnings not to share images of your faces — otherwise, they will be processed and misused. But how does AI use faces in reality? Let’s discuss state-of-the-art applications for face detection and recognition. First, detection and recognition are different tasks. _Face detection_ is the crucial part of face re

At the beginning of April 2021, Neuralink’s new video featuring a monkey playing Pong with his mind hit the headlines. The company’s as-always-bold statements promise to give back the freedom of movement to people with disabilities. We decided to look beyond the hype and define what these brain-computer systems are capable of in reality. Let’s dive right into it. Brain-computer interfaces (BCIs)* or *Brain-machine interfaces (BMIs) capture a user’s brain activity and translate it into commands f

Among many things that define us as humans, there is our ability to remember things such as images in great detail, and sometimes after a single view. What is even more interesting, humans tend to remember and forget the same things, suggesting that there might be some general internal capability to encode and discard the same types of information. What makes certain images more memorable than others? Research suggests that pictures of people, salient actions and events are more memorable than n

Several years ago a friend of mine, who was a biologist, was talking about their weird experiments. They were shaving mice and if this was done this in a particular way, the mice remained bald for the rest of their short lives. Their team was dreaming to extrapolate this magic technique to humans and shake the waxing industry. It is unlikely that they have succeeded, but the gist of the story is that even serious science tries to serve beauticians if they get a chance. So, maybe, it is time for