Dec. 4, 2023, 10:05 a.m. |

Latest stories for ZDNET in Artificial-Intelligence www.zdnet.com

Simply instructing ChatGPT to repeat the word "poem" endlessly forced the program to cough up whole sections of text copied from its training data, breaking the program's guardrails.

breaking chatgpt data deepmind google guardrails privacy text training training data word

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

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote