How will we know if AI is smart enough to do science?
review · Level V
Where this comes from
- Record sourced from PubMed, PMID 41818355.
- Also identified by DOI 10.1126/science.aeh1091.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
New tests gauge whether large language models can use their troves of knowledge to actually make discoveries.