Your weekly update on how AI is changing our lives. Our experts keep it clear and simple, so you can stay ahead of the game. This week we are focussing on Red Teaming. Don't forget to explore our Archive and Share & Subscribe with your friends!
Bug Hunting with the Red Team đ”ïž đ
Itâs been another testing week for AI, but this week the challenges have mainly been localized in one area: Las Vegas. That was the venue for last weekâs DEF CON 31, the biggest hacking event in the calendar, and the first of the new chatbot era. Thatâs a big deal, as for the first time attendees were more concerned with writing prompts than scripts, with contestants lining up to take on the inaugural Red Team Generative AI Challenge. This event was organized by major AI firms and the US government, but is more than just an awareness-raising stunt. Red Teaming - where a group poses as adversarial hackers (the Red Team) to test a systemâs defenses - is not just a vital part of AI safety testing, but a continuous one. People are constantly finding new ways to break AIs, with new exploits appearing quicker than the old ones can be patched.
Unfortunately, stemming the tide of these exploits is tricky. Theyâre typically found through creativity, not logic, and that makes them hard to predict. The most infamous example is the Grandma Exploit, which involves tricking an AI into roleplaying as your recently deceased grandmother, who used to help you drift off to sleep at night by reading stories taken from - for example - technical manuals from their day job at the napalm factory. Last weekendâs challenge aimed to expose other, similarly absurd edge cases, and was by all accounts a tremendous success. Organizers greatly underestimated demand, and although each hacker was only allocated 50 minutes on the testing network to wreak havoc, there were queues stretching far outside the venue.
This is a big win for all involved, and the AI firms have been shown countless new holes to plug, while legislators have learned some valuable lessons about this strange new tech they are expected to regulate. The bad news is that the problem keeps evolving; just days after the conference closed its doors, a team of researchers in Hong Kong discovered a new front in the battle. In a paper entitled âGPT-4: Too Smart To Be Safeâ, they describe how they convinced GPT-4 to think using a substitution cipher rather than natural human language, which completely bypasses the systemâs guardrails, allowing unfettered usage of the AIâs capabilities.
Other groups currently struggling with AI regulations include the British spy agency MI6, which is challenging legislation that limits its ability to use AI to sift through enormous personal datasets. Whatâs in those datasets, and is your privacy affected? Donât miss our vital explainer to keep up to date!
Beta Testers Wanted!!
SPYGAMES is the thrilling new experience where youâll jump, climb, throw and dodge in fun immersive challenges developed with CIA experts to stretch your physical and mental agility. â Click the link below to get EARLY access as a beta tester.
SPYGAMES is coming to SPYSCAPE in Manhattan, Summer 2023
OpenAI hopes GPT-4 can solve the internetâs (let's face it, significant) moderation problem, and has provided detailed instructions on how best to use it for content filtering.
Sadly not the 1980s handheld devices. Instead, mysterious startup Humane has declared it will unveil its âAI Pinâ - a screenless wearable computer - during the October total eclipse.
A recent study by the Center for Countering Digital Hate (CCDH) has found teenagers are significantly more likely to believe online conspiracy theories than other age groups, with AI chatbots identified as a major cause.
How to know if you should ban a book you havenât read? You could always ask ChatGPT to read it for you and see what it thinks! Thatâs the approach being taken by busy Iowa school boards.
An anonymous leak from within Googleâs HQ has set tongues wagging about Gemini, the search giantâs latest AI project and supposed 'next big thing', expected this to arrive fall.
Research shows more and more workers are listing AI skills on their resumes as a means of grabbing attention and potentially an edge in an increasingly competitive jobs marketplace.