From Science

We read the papers. You get the plain version.

Studies, benchmarks and breakthroughs become knowledge you can decide on. With sources, limits, and the question of what a result really means outside the lab.

3 articles

A benchmark is not a place of work. The interesting part begins where controlled conditions meet real processes.

Benchmark Performance ≠ Bedside Performance

An AI model diagnoses with 87% accuracy, and it can still be dangerous in the clinic. Why study numbers don’t tell us what we want to hear, and what counts instead.

5 min read · Read02

37 Percent of AI Citations Don't Exist

Oscar works in peer review at a medical journal. What he now sees there: submissions whose references lead nowhere, author names that are wrong, titles that were pulled out of thin air. A survey of a silent crisis.

4 min read · Read03

Validation Is No Longer Enough

A scalpel sits on a shelf until someone needs it. An AI model keeps learning, drifts, adapts, and in doing so falls through every grid built for static medical devices. Why the EU approval system has to be fundamentally rethought for adaptive AI.

5 min read · Read