How the new version of ChatGPT generates hate and disinformation on command

calendar Jun 1, 2024  ·
Share on: linkedin copy

OpenAI's latest language model, GPT-4o, was launched in mid-May. The new version of the popular artificial intelligence chatbot isn't supposed to spout racist screeds or conspiracy theories. But an investigation by Radio-Canada's Décrypteurs team found it's easy to disarm the guardrails.

Read more here: External Link