Skip to main content

Share story

AI Science

Study finds AI exam answers outperform many law students

Study finds AI exam answers outperform many law students Image: Primary
Researchers testing nine AI models on University of Wollongong law exams found that their criminal law answers averaged 76.3%, above the scores of 82.5% of students. In tort law, the AI answers averaged 66%, above 61% of students. The results mark a change from the researchers' 2023 criminal law test, when AI answers averaged 52.5% and scored around the 22nd percentile. The models produced 18 papers across two subjects, and some answers had weak citations or fabricated authorities. The authors say the results raise concerns about unsupervised assessment, while the small, single-university test does not establish that the models are reliable legal experts.
Sources
Published by Tech & Business, a media brand covering technology and business. This story was sourced from Phys.org and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Security
Security

Fullerton Health says breach compromised about 140,000 work pass records

Fullerton Health said on November 14 that about 140,000 work pass holder records were compromised in a breach of its Migrant Worker Primary Care Plan programme in Singapore. About 43,000 records belonged to people whose work passes were no longer valid, CNA reported.

AI Capital
AI Capital

Luminal raises $25 million Series A led by Standard Capital

Luminal raised a $25 million Series A led by Standard Capital, CEO Joe Fioti told Axios Pro. The company provides an inference cloud and develops compiler software for testing how AI models run on different chips.

Capital AI
Capital AI

WhiteMatter raises $20 million Series A for AI agent oversight

WhiteMatter raised a $20 million Series A, Business Insider reported. Founded in 2024, the startup builds AI agents designed to oversee other AI agents, monitoring their file access, software use, decision making, and actions. It calls these oversight systems "guardian" agents.

Policy Products
Policy Products

Italian privacy authority fines Meta €805 million over gallery access

The Italian Data Protection Authority imposed a fine of €805 million ($887 million) on Meta Platforms Inc. The penalty concerns Meta's access to photos and videos in the galleries of Android users without those users' explicit consent.