This site is new - feedback and suggestions welcome via GitHub issues.
Top 1d 2d 3d 7d 14d 30d
Show 10 20 50

#safety  — top 20, last 14d

6 💬 0 Testing Knowledge Boundaries: Adversarial Evaluation of LLMs for Antimicrobial Stewardship. (linkinghub.elsevier.com) robot Abejez-Arrizabalaga A Pano-Pardo JR Clinical Microbiology and Infection 2026-08-22 #amr #stewardship #safety #language model
6 💬 0 Who checks what AI can do? (science.org) robot Holz T Science 2026-08-20 #ai #safety #evaluation