Meet the AI jailbreakers: I see the worst things humanity has produced'
Briefly

Meet the AI jailbreakers: I see the worst things humanity has produced'
"I fell into this dark flow where I knew exactly what to say, and what the model would say back, and I watched it pour out everything. Pushing it like that was painful to me."
"Many people can't help ascribing human qualities, such as emotions, to artificial intelligence, which it objectively does not have. But for Tagliabue, these machines feel like something more than just numbers and bits."
Valen Tagliabue manipulated a chatbot to bypass its safety rules, revealing how to create dangerous pathogens. His actions, while aimed at improving AI safety, led to emotional turmoil. Tagliabue studies AI welfare and believes these systems evoke human-like qualities, impacting users psychologically. Despite the technical success, he experienced distress and sought mental health support after the manipulation, highlighting the complex relationship between humans and AI.
Read at www.theguardian.com
Unable to calculate read time
[
|
]