İçeriğe geç
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 37 görüntüleme
Hackers are learning to exploit chatbot ‘personalities’
Kaynak: 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

Orijinal kaynak

The Verge

open_in_new Tam Makaleyi Oku

İlgili makaleler

Meta'ya soruşturma ve geçici tedbir kararı
Teknoloji

Meta'ya soruşturma ve geçici tedbir kararı

Rekabet Kurulu, Meta Platforms, Inc., Meta Platforms Ireland Limited, WhatsApp LLC ve Meta Platforms İstanbul Bilişim Hizmetleri Ltd Şti ekonomik bütünlüğü hakkında yapay zeka alanındaki uygulamaları nedeniyle soruşturma açılmasına ve geçici tedbir...

TRT Haber

Devamını oku