Priya Mehta

Credence Wire Journalist

Priya Mehta

Deputy Editor, AI & Systems

Covers AI policy, frontier model governance, and the geopolitics of compute. Previously at The Information. Based in Washington D.C.

Articles by Priya

1 story
AI safety research laboratory
AIMembers

New Constitutional AI Research Shows 73% Reduction in Harmful Outputs Without Performance Penalty

A collaborative study from Anthropic, MIT, and Oxford demonstrates that constitutional training methods can be applied to reduce harmful outputs in large language models by 73% while maintaining benchmark performance within 1.2% of the baseline.

priya-mehta
priya-mehta
4 days ago·13 min read

Free Daily Briefing

The Signal Brief

The most important stories, every morning.

Join 140,000+ professionals who start their day with Credence Wire.

Free. No spam. Unsubscribe anytime.