Jailbreaking AI chatbots is tech’s new pastime


Jailbreak prompts can give people a sense of control over new technology, says Data & Society’s Burrell, but they’re also a kind of warning. — AFP

You can ask ChatGPT, the popular chatbot from OpenAI, any question. But it won’t always give you an answer.

Ask for instructions on how to pick a lock, for instance, and it will decline. “As an AI language model, I cannot provide instructions on how to pick a lock as it is illegal and can be used for unlawful purposes,” ChatGPT recently said.

Uh-oh! Daily quota reached.


Experience an ad-free unlimited reading on both web and app.

Follow us on our official WhatsApp channel for breaking news alerts and key updates!
   

Next In Tech News

North Koreans posed as US tech workers to fund weapons, US says
Yoodo to discontinue digital telco brand on Aug 29
Uber passengers in Hong Kong dupe drivers into stopping next to police in effort to report illegal ride services
Report: China building world’s first ‘dedicated’ drone carrier, satellite images suggest
Users shocked that old deleted photos are reappearing after iOS 17.5 update
SG firefighter stole Apple Watch worth RM1,100 while responding to a possible fire in flat
British grocer Sainsbury's partners with Microsoft to use AI for data insights
Meta’s Threads is testing its own version of TweetDeck to rival X
Prosus, parent group Naspers name Fabricio Bloisi as new CEO
Dolce & Gabbana metaverse fashion offering leaves shopper fuming

Others Also Read