People are 'Jailbreaking' ChatGPT to Make It Endorse Racism
Por um escritor misterioso
Descrição
Convincing an AI that it's playing a role and "scaring" it into violating safety filters is one way to get a chatbot to break bad.
Six questions about Google Bard - by Casey Newton
AI bot that lets you chat with Jesus, Hitler is latest GPT-3 controversy
AI incidents and 'networked trouble': The case for a research agenda - Tommy Shaffer Shane, 2023
jailbreak - VICE
Comments - Jailbreaking ChatGPT on Release Day
Bob Hayes, PhD en LinkedIn: People are 'Jailbreaking' ChatGPT to Make It Endorse Racism, Conspiracies
ChatGPT, an AI chatbot, has gone viral. Some say it's better than Google; others worry it's problematic.
Sustainability Report2023
ChatGPT-Dan-Jailbreak.md · GitHub
Lessons in linguistics with ChatGPT: Metapragmatics, metacommunication, metadiscourse and metalanguage in human-AI interactions - ScienceDirect
Frontier AI: capabilities and risks – discussion paper
de
por adulto (o preço varia de acordo com o tamanho do grupo)