Students find AI isn't a cure all for drug discovery
There's been a lot of talk about artificial intelligence's potential to transform drug research and discovery—and companies are spending billions in pursuit of that dream.
Recent studies by Northeastern University graduate students suggest that artificial intelligence, while beneficial in certain aspects, is not a panacea for drug discovery. Over the past year, students in Anton Sinitskiy's Applied AI capstone course tested popular open-source AI frameworks like GPT Researcher and Agent Laboratory.
Their findings indicate that while AI can assist in some applications, it still struggles with accuracy, reliability, and the ability to generate well-sourced scientific reports independently. The students found that even advanced AI models made factual mistakes, required constant guidance, and were unable to reproduce complex algorithms.
Despite these challenges, the researchers acknowledge that AI can still be useful for repetitive tasks and stress-testing ideas, but users must be cautious and verify the reliability of AI-generated information.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
