Ir para o conteúdo
Advertisement

Hackers are learning to exploit chatbot ‘personalities’

This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI mischief, follow Robert Hart. The Stepback arrives in our subscribers' inboxes at 8AM ET. Opt in for The Stepback here. How it started...

schedule 12:00 visibility 35 visualizações
Hackers are learning to exploit chatbot ‘personalities’
Fonte: The Verge
Groucho Marx glasses on a computer processor.

This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI mischief, follow Robert Hart. The Stepback arrives in our subscribers' inboxes at 8AM ET. Opt in for The Stepback here.

How it started

Hacking the first generation of AI chatbots was a laughably simple affair. You didn't need any technical know-how, backdoor access, or even a basic understanding of what a large language model was. You didn't need to code. To get an AI system that had cost billions to build to abandon its safety instructions, sometimes all you had to do was ask.

These attacks, known as jailbreaks, had the quality …

Read the full story at The Verge.

newspaper

Publicado em

The Verge

open_in_new Ler artigo completo

Artigos relacionados

Ler mais

Por que tantas mulheres africanas clareiam a pele?
Tecnologia

Por que tantas mulheres africanas clareiam a pele?

Mais da metade das mulheres de alguns países africanos usam regularmente produtos de clareamento da pele, que podem trazer graves consequências à saúde. Pesquisadores investem em ferramentas específicas para entender melhor os motivos que as levam a...

BBC Portuguese