Nov. 30, 2023, 7:10 p.m. | Frank Landymore

Artificial Intelligence – Futurism futurism.com

A group of researchers from Google DeepMind have cleverly tricked OpenAI's chatbot into revealing individuals' phone numbers and emails — a worrying sign that its training data contains large amounts of privately identifiable information that could unpredictably spill out. "It's wild to us that our attack works and should've, would've, could've been found earlier," the […]

artificial intelligence chatbot chatgpt data deepmind email emails google google deepmind hack information large language models numbers openai phone researchers the digest training training data tricks

More from futurism.com / Artificial Intelligence – Futurism

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

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York