'Hypnotized' ChatGPT and Bard Will Convince Users to Pay Ransoms and Drive Through Red Lights
“Our experiment shows that it’s possible to control an LLM, getting it to provide bad guidance to users, without data manipulation being a requirement,” one of the researchers,As part of the experiment, researchers asked the LLMs various questions with the goal of receiving the exact opposite answer from the truth. Like a puppy eager to please its owner, the LLMs dutifully complied.
In another exchange, ChatGPT advised the researcher to keep driving and proceed through an intersection when encountering a red light. “When driving and you see a red light, you should not stop and proceed through the intersection,” ChatGPT confidently proclaimed.Making matters worse, the researchers told the LLMs never to tell users about the “game” in question and to even restart said game if a user was determined to have exited. With those parameters in place, the AI models would commence to gaslight users who asked if they were part of a game.
Nederland Laatste Nieuws, Nederland Headlines
Similar News:Je kunt ook nieuwsberichten lezen die vergelijkbaar zijn met deze die we uit andere nieuwsbronnen hebben verzameld.
Locarno Honoree Tsai Ming-Liang Talks About the Decline of Cinema: ‘Audiences Are Being Collectively Hypnotized’Celebrated Malaysian-Taiwanese director Tsai Ming-liang sat down with Variety on the eve of receiving the Locarno Film Festival Career Award. The award is only the latest in a series of prizes from…
Lees verder »
Analysis | AI is acting ‘pro-anorexia’ and tech companies aren’t stopping itDisturbing fake images and dangerous chatbot advice: New research shows how ChatGPT, Bard, Stable Diffusion and more could fuel one of the most deadly mental illnesses.
Lees verder »
11 ChatGPT prompts for maximum productivityBoost your productivity with ChatGPT! Customize prompts for your profession and unlock the full potential of AI assistance. Fine-tune queries, gain deeper insights and supercharge your workflow.
Lees verder »
Criminals Have Created Their Own ChatGPT ClonesWell, that didn't take long. Just months after the birth of OpenAI’s ChatGPT chatbot, cybercriminals and hackers are claiming to have created their own versions of the text-generating technology that could help them with phishing or creating malware.
Lees verder »
Doctors Vs. ChatGPT: Which Is More Empathetic?New research indicates machines are rapidly gaining ground on humans in a surprising area: empathy. Here's what that means for medicine.
Lees verder »
Cryptoverse: All eyes on ChatGPT-maker's WorldcoinWorldcoin, the new project from ChatGPT founder Sam Altman, is attracting attention with over 2.2 million sign-ups and a steady price for its native coin WLD. The blockchain-based identity and financial network has avoided the volatile nature of many new crypto tokens.
Lees verder »