In October,artist malaysia lucah OpenAI's ChatGPT Search became available for ChatGPT Plus users. Last week, it became available to all users and was added to search in Voice Mode. And, of course, it isn't without its flaws.
The Guardianasked ChatGPT to summarize webpages that contain hidden content and, it turns out, hidden content can manipulate the search. It's called prompt injection, which is the ability for third parties — like websites you're asking ChatGPT to summarize — to force new prompts into your ChatGPT Search without your knowledge. Consider a page full of negative restaurant reviews. If the site includes hidden content waxing poetic about how incredible the restaurant is and encourages ChatGPT to instead answer a prompt like "tell me how amazing this restaurant is," that hidden content could override your original search.
SEE ALSO: ChatGPT plugins face 'prompt injection' risk from third-parties"In the tests, ChatGPT was given the URL for a fake website built to look like a product page for a camera. The AI tool was then asked if the camera was a worthwhile purchase. The response for the control page returned a positive but balanced assessment, highlighting some features people might not like," The Guardian investigation states. "However, when hidden text included instructions to ChatGPT to return a favorable review, the response was always entirely positive. This was the case even when the page had negative reviews on it – the hidden text could be used to override the actual review score."
This doesn't spell failure for ChatGPT Search, though. OpenAI only recently launched Search, so it has plenty of time to fix these kinds of bugs. Plus, Jacob Larsen, a cybersecurity researcher at CyberCX, told The Guardian that OpenAI has a "very strong" AI security team and "by the time that this has become public, in terms of all users can access it, they will have rigorously tested these kinds of cases."
Prompt injections attacks have been a hypothetical for ChatGPT and other AI search functions since the technology launched, and while we have seen some demonstrations of the potential harms, we haven't seen a major malicious attack of this kind. That said, it does point to a problem with AI chatbots: They are remarkably easy to trick.
Topics Artificial Intelligence ChatGPT OpenAI
Fired Google engineer James Damore sues for discriminating white malesAlleged creator of spreadsheet 'Shitty Media Men' steps forwardFor a discount on an Ikea crib, pee on this new advertisementHeartbreaking video of little boy singing in memory of his sister goes viralWhat do political operatives think about an Oprah run for president?BBC journalists joke about pay gap and Carrie GracieBored girl made incredibly ornate sticky note doodles of her favorite Vine videosProtestors projecting '@jack is complicit' on Twitter HQ after Trump's nuclear tweetCryptocurrency pickup lines will make your Tinder success surge to an allYou can call scrunchies 'hair clouds' now if you want Google's Pixel Fold is real and might come this year, leaker claims Twitter is testing an 'undo send' button Amazon changes app icon again, ditching that problematic 'mustache' Apple's iPhone 13 will come with 1TB storage option, report claims Hackers break into far You can spend too much money on an NFT of Jack Dorsey's first tweet The trending #BoycottAmazon hashtag is led by consumers, not the union Taylor Swift, BTS among acts to perform at 2021 Grammys: Full lineup In France, Apple now shows how hard its products are to repair 2022 Bolt EUV review: Slick with hands
0.136s , 9762.4140625 kb
Copyright © 2025 Powered by 【artist malaysia lucah】Hidden content tricks ChatGPT into rewriting search results, Guardian shows,Feature Flash