Tampering with Generative Artificial Intelligence by Jailbreaking|Manipolare l’intelligenza artificiale generativa attraverso il jailbreaking

In this paper, I will analyse the risks linked to the use of generative artificial intelligence systems and relative risk-reduction strategies, while concentrating in particular on the possibility of tampering with the chat bot Chat GPT by jail breaking. After examining how a user can tamper with this generative AI, bypassing its ethical and legal restrictions, through a series of prompts, I will turn my focus to the ethical issues raised by the malicious use of this technology: are the transparency requirements requested of generative AI sufficientor should there be tighter restrictions that do not hinder the innovation and development of these technologies? How can the risk of tampering with these AI tools be lowered? And, should a breach take place, who is responsible: the AI developer or the jail breaker? To what extent could the changes needed to prevent jail breaking involuntarily generate or strengthen certain biases? Inconclusion, I will uphold the necessity of ethical reflection for the sustaina bleand “human-centric” development of AI.