May 10, 2024, 3 p.m. | Hannah Devlin Science correspondent

Artificial intelligence (AI) | The Guardian www.theguardian.com

Researchers find instances of systems double-crossing opponents, bluffing, pretending to be human and modifying behaviour in tests

They can outwit humans at board games, decode the structure of proteins and hold a passable conversation, but as AI systems have grown in sophistication so has their capacity for deception, scientists warn.

The analysis, by Massachusetts Institute of Technology (MIT) researchers, identifies wide-ranging instances of AI systems double-crossing opponents, bluffing and pretending to be human. One system even altered its …

ai systems artificial intelligence (ai) board board games capacity computing conversation deception decode games human humans instances proteins researchers science scientists systems technology us news world news

More from www.theguardian.com / Artificial intelligence (AI) | The Guardian

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US