Robin: the AI that designs experiments but does not carry them out
Un robot no eligió solo la molécula correcta para tratar una enfermedad incurable del ojo: la propuso, y después un laboratorio real confirmó que funcionaba. Phys.org documentó en septiembre de 2026 cómo varios grupos ya consiguen que sus sistemas de inteligencia artificial generen una hipótesis biológica y la validen experimentalmente sin que un investigador decida el paso intermedio: es uno de…
A robot named Robin, developed by the non-profit lab FutureHouse, proposed a potential treatment for age-related macular degeneration, a currently incurable eye disease. In 2025, Robin suggested reusing the ROCK inhibitor ripasudil, already approved in Japan for glaucoma, and a collaborating lab confirmed its effectiveness in an experiment.
This marks one of the first public cases of autonomous scientific AI in biology, where the AI system generated a hypothesis, designed an experiment, and had it validated without human intervention. This achievement builds on previous AI systems like Adam and Eve, which automated parts of the scientific process, but Robin's ability to work with external labs and validate results experimentally is a significant advancement.
Google also presented a similar AI system in February 2025, but it required human input to select which hypothesis to test.
Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.