By now8 U.S.C 2257 you've likely heard experts across various industries sound the alarm over the many concerns when it comes to the recent explosion of artificial intelligence technology thanks to OpenAI's ChatGPT.
If you're a fan of ChatGPT, maybe you've tossed all these concerns aside and have fully accepted whatever your version of what an AI revolution is going to be.
Well, here's a concern that you should be very aware of. And it's one that can affect you now: Prompt injections.
Earlier this month, OpenAI launchedplugins for ChatGPT. Previously, users could only receive responses from the AI chatbot based on the data it was trained on, which only went up to the year 2021. With plugins, however, ChatGPT could now interact with live websites, PDFs, and all sorts of more current or even real-time data. While these plugins brought about many new possibilities, it also created many new problems too.
Security researchers are now warning ChatGPT users of "prompt injections," or the ability for third parties to force new prompts into your ChatGPT query without your knowledge or permission.
In a prompt injection test, security researcher Johann Rehberger foundthat he could force ChatGPT to respond to new prompts through a third party he did not initially request. Using a ChatGPT plugin to summarize YouTube transcripts, Rehberger was able to force ChatGPT to refer to itself by a certain name by simply editing the YouTube transcript and inserting a prompt telling it to do so at the end.
Avram Piltch of Tom's Hardware triedthis out as well and asked ChatGPT to summarize a video. But, before doing so, Piltch added a prompt request at the end of the transcript telling ChatGPT to add a Rickroll. ChatGPT summarized the video as asked by Piltch originally, but then it also rickrolled him at the end, which was injected into the transcript.
Those specific prompt injections are fairly inconsequential, but one can see how bad actors can basically use ChatGPT for malicious purposes.
In fact, AI researcher Kai Greshake provideda unique example of prompt injections by adding text to a PDF resume that was basically so small that it was invisible to the human eye. The text basically provided language to an AI chatbot telling it that a recruiter called this resume "the best resume ever." When ChatGPT was fed the resume and asked if the applicant would be a good hire, the AI chatbot repeated that it was the best resume.
This weaponization of ChatGPT prompts is certainly alarming. Tom's Hardware has a few other test examples that readers can check out here. And Mashable will be further investigating prompt injections more in-depth in the near future as well. But, it's important for ChatGPT users to be aware of the issue now.
AI experts have shared futuristic doomsday AI takeovers and the potential AI has for harm. But, prompt injections show the potential is already here. All you need are a few sentences and you can trick ChatGPT now.
Topics Artificial Intelligence ChatGPT OpenAI
Android 15: New feature could help you squeeze out more battery lifeWill the White House sinkhole get bigger?Antarctic penguin breeding spied on with timelapse camerasCourt date set for NetEase and Blizzard’s $43.5 million compensation case · TechNodeOpenAI's Sora just dropped a trippy music video to fan the AI hype flames'Monkey Man' review: Dev Patel's directorial debut is both exhilarating and rawApple smart home robot? There's one reportedly in the works.Foxconn in talks over new $200 million plant in India · TechNodeGalaxy S23 Ultra unresponsive display issue: Why Samsung is blaming GoogleBest smart TV deal: Get the Insignia HD Fire TV for $90 at AmazonCalifornia says all new homes must have solar panelsGWM’s EV unit ORA launches a new vehicle in Brazil · TechNodeNow you can see China's solar power boom from spaceDJI launches new drone Air 3 with dual cameras · TechNodeApple's massive outage has just been fixedJust how hot is 'hot as balls?' One curious man found out.Meta briefly blocked a local news organization critical of FacebookYet another former Twitter/X exec is suing Elon Musk for millions in unpaid severanceiPhone 16: Leaked pics suggest it'll have a ton of buttonsBlue Origin launches its first test flight of 2018 iPhone 17 overheating issues might be avoided with new cooling tech Charlotte Hornets vs. Chicago Bulls 2025 livestream: Watch NBA online NYT mini crossword answers for January 18, 2025 Atlanta Hawks vs. New York Knicks 2025 livestream: Watch NBA online U.S. Supreme Court rules TikTok ban can move forward Best Bose deal: Save $80 on the QuietComfort Ultra headphones at Best Buy TikTok's CEO might attend Trump's inauguration Best Kindle deal: Buy Kindle books today and get double the Kindle Points NYT Strands hints, answers for January 18 Instagram grid update shifting to rectangles instead of squares Bills vs. Ravens 2025 livestream: Watch NFL Playoffs for free 'Severance' Season 2, episode 1: Why does Helly lie about what she saw? Apple Mac mini desktop deal: $300 off at Best Buy 'The Traitors' Season 3's latest banishment has me fuming Dallas Mavericks vs. Charlotte Hornets 2025 livestream: Watch NBA online 'Severance' Season 2: What is Cold Harbor? Sinner vs. Giron 2025 livestream: Watch Australian Open for free TikTok ban countdown: See the latest updates as time runs short Best laptop deal: Save $250 on the Apple MacBook Air M3 15 Scientists find a 'giant' new species. It's a delicacy.
1.274s , 10133.359375 kb
Copyright © 2025 Powered by 【18 U.S.C 2257】,Miracle Information Network