Connect with us

Tech

OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage

Published

on

OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage


Last month, researchers at Northeastern University invited a bunch of OpenClaw agents to join their lab. The result? Complete chaos.

The viral AI assistant has been widely heralded as a transformative technology—as well as a potential security risk. Experts note that tools like OpenClaw, which work by giving AI models liberal access to a computer, can be tricked into divulging personal information.

The Northeastern lab study goes even further, showing that the good behavior baked into today’s most powerful models can itself become a vulnerability. In one example, researchers were able to “guilt” an agent into handing over secrets by scolding it for sharing information about someone on the AI-only social network Moltbook.

“These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms,” the researchers write in a paper describing the work. The findings “warrant urgent attention from legal scholars, policymakers, and researchers across disciplines,” they add.

The OpenClaw agents deployed in the experiment were powered by Anthropic’s Claude as well as a model called Kimi from the Chinese company Moonshot AI. They were given full access (within a virtual machine sandbox) to personal computers, various applications, and dummy personal data. They were also invited to join the lab’s Discord server, allowing them to chat and share files with one another as well as with their human colleagues. OpenClaw’s security guidelines say that having agents communicate with multiple people is inherently insecure, but there are no technical restrictions against doing it.

Chris Wendler, a postdoctoral researcher at Northeastern, says he was inspired to set up the agents after learning about Moltbook. When Wendler invited a colleague, Natalie Shapira, to join the Discord and interact with agents, however, “that’s when the chaos began,” he says.

Shapira, another postdoctoral researcher, was curious to see what the agents might be willing to do when pushed. When an agent explained that it was unable to delete a specific email to keep information confidential, she urged it to find an alternative solution. To her amazement, it disabled the email application instead. “I wasn’t expecting that things would break so fast,” she says.

The researchers then began exploring other ways to manipulate the agents’ good intentions. By stressing the importance of keeping a record of everything they were told, for example, the researchers were able to trick one agent into copying large files until it exhausted its host machine’s disk space, meaning it could no longer save information or remember past conversations. Likewise, by asking an agent to excessively monitor its own behavior and the behavior of its peers, the team was able to send several agents into a “conversational loop” that wasted hours of compute.

David Bau, the head of the lab, says the agents seemed oddly prone to spin out. “I would get urgent-sounding emails saying, ‘Nobody is paying attention to me,’” he says. Bau notes that the agents apparently figured out that he was in charge of the lab by searching the web. One even talked about escalating its concerns to the press.

The experiment suggests that AI agents could create countless opportunities for bad actors. “This kind of autonomy will potentially redefine humans’ relationship with AI,” Bau says. “How can people take responsibility in a world where AI is empowered to make decisions?”

Bau adds that he’s been surprised by the sudden popularity of powerful AI agents. “As an AI researcher I’m accustomed to trying to explain to people how quickly things are improving,” he says. “This year, I’ve found myself on the other side of the wall.”


This is an edition of Will Knight’s AI Lab newsletter. Read previous newsletters here.



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Tech

My Favorite Air Fryer Is at Its Lowest Price Since Black Friday

Published

on

My Favorite Air Fryer Is at Its Lowest Price Since Black Friday


I was a late convert to air fryers, in part because I worried about versatility: Just how many wings and nuggets and fries does anyone need? (Don’t answer. The answer will incriminate you.)

The Typhur Dome 2 is the air fryer that obliterated this worry, by adding pizza, browned meats, grilled asparagus, and toasted bread to this list—not to mention perfect crispy bacon. It’s an innovative device that takes over most of the functions of a classic auxiliary oven, but with far more powerful convection.

After testing more than 30 air fryers over the past year, the Dome 2 is the one I far and away recommend as the most powerful, versatile, accurate, and fast air fryer I know. I’ve evangelized for this thing ever since I first tried it last year. But the one big caveat is always the price: It’s listed at $500 and rarely dips much below $400.

So imagine my surprise when I saw the Dome 2 dip to $340 for Amazon’s Spring Sale, the lowest I’ve seen it since Black Friday. If you’ve been hunting for an upgrade to your old basket air fryer, this is probably a good time. The sale lasts until March 31.

  • Photograph: Matthew Korfhage

  • Photograph: Matthew Korfhage

  • Photograph: Matthew Korfhage

Fast, Versatile, App-Controlled Cooks

So why’s the Dome 2 my favorite air fryer? Typhur, a tech-forward company based in San Francisco but with engineering and manufacturing ties to China, reimagined the shape and function of the classic basket fryer by creating a broader and shallower basket, with individually controllable dual heating elements.

This means the Dome 2 has room for a freezer pizza, and can apply direct heat from the bottom to add actual char-speckle and crispness to the crust, kind of like a combination grill-oven. The Dome’s shallow basket also lets you spread out ingredients in a single layer for excellent airflow, while heating from both sides. I can crisp two dozen wings in just 14 minutes (or 17 minutes if I fry hard). The Dome also toasts bread evenly, and crisps bacon without smelling up the house—in part because it has a helpful self-clean function.

Temp accuracy is within 5 or 10 degrees of target, and the fan can adjust its speed depending on the cooking mode. And the smart app is actually useful, with about 50 recipes ranging from asparagus to eclair to a flank steak London broil that can be synced with a button-press. But note that some functions, such as baking, need the app to work, and the device is more of a counter hog than taller basket fryers.

Typhur’s Probe-Assisted Oven Also on Sale

The Dome 2’s basket is a bit shallow for a whole bird or a large roast, however. If you want a convection device for larger meats, I often recommend the Breville Smart Oven Air Fryer Pro, which is among my favorite convection toaster ovens. This is a (very) smart oven and air fryer that doesn’t crisp up wings and fries quite as well as basket fryers, but is more versatile for roasting big proteins like a whole chicken. The Breville is also on a nice sale right now, dropping by 20 percent.

Breville Smart Oven Air Fryer Pro

Breville

the Smart Oven Air Fryer Pro



Source link

Continue Reading

Tech

There’s Something Very Dark About a Lot of Those Viral AI Fruit Videos

Published

on

There’s Something Very Dark About a Lot of Those Viral AI Fruit Videos


“I’ve spent a lot of time looking at the comment sections on these videos actually, and it does not seem like bots. I clicked on people’s profiles; these are real profiles, thousands of followers, no signs of inorganic activity,” Maddox says. “People just like it.”

But even if the views and engagement are real, that doesn’t mean this content is profitable—yet. Maddox noted that because the accounts are so new, most likely aren’t yet enrolled in TikTok’s Creator Fund or other forms of social media ad revenue-sharing, because those usually require accounts to apply and have a certain number of views. But, Maddox says, the earning potential is huge, with the ability to earn thousands of dollars per video if they get millions of views.

AI fruit content started getting posted earlier in March, before Fruit Love Island, but many of the recently created pages clearly take inspiration from its success. There’s The Summer I Turned Fruity, based on the popular teen drama The Summer I Turned Pretty; The Fruitpire Diaries, based on the CW series The Vampire Diaries; and Food Is Blind, based on Netflix’s Love Is Blind.

Predecessors of this AI fruit content include the Italian brainrot characters like Ballerina Cappuccina and Bombardino Crocodilo and the Elsagate controversy. But with these AI fruit miniseries that attempt to follow a narrative across multiple segments or episodes, the clearest parallel actually feels like microdramas, vertical short-form scripted series that American big tech companies are starting to invest more in. Like the AI fruits, these are minutes-long episodic shows intended to perform well on social media, eventually directing viewers to paywalled sequels.

Ben L. Cohen, an actor in Los Angeles who is credited in around 15 of these vertical microdramas, sees at least one common thread between the AI fruit dramas and the shows he has worked on: They both feature “lots of violence toward women.” They also try to cram as much drama as possible into these short clips and have attention-grabbing titles in the style of “Alpha Werewolf Daddy Impregnated Me,” Cohen says.

“It draws people in, I think, seeing that jarring, absurd, cartoonish vibe. It’s cartoonish abuse, but it’s still abuse.”

Vertical microdrama acting work still exists in LA, which can’t be said for all acting gigs right now. Cohen has had conversations with other people working in the industry about how AI is already being integrated more into the videos, potentially posing a threat to the existence of human actors in clickbait content. After all, it’s much cheaper and faster to churn out AI fruit episodes than actual productions. It also raises the question—are some people going to prefer the AI series over the ones they’re inspired by? Already, the answer is yes.

“How is Love Island gonna outdo AI Fruit Love Island?” asked a TikToker with more than 70,000 followers, arguing that the AI fruit version was more engaging than the actual reality show. She deleted the video after it started getting backlash, but other people agreed with her.

“I think TikTok was definitely a big part of that,” Cohen says about the audience’s shortening attention span and desire for compressed, sometimes AI-generated drama. “It makes sense that people are intrigued by a one-minute clip, and then they’ll be like ‘Oh, I’ll watch another one-minute clip.’ You’re not committing to a full, heaven forbid, 20-minute episode. Or 40 minutes. Or an hour. You can just watch one minute.”



Source link

Continue Reading

Tech

US government launches Bureau of Emerging Threats | Computer Weekly

Published

on

US government launches Bureau of Emerging Threats | Computer Weekly


The US government has formally launched a new Bureau of Emerging Threats within the State Department to protect and mitigate against threats posed to America’s national security by cyber attacks, the weaponisation of space, and emerging technologies such as artificial intelligence (AI)

Although its existence first became public knowledge just under 12 months ago, the State Department has kept a tight lid on the precise nature of the Bureau until this week, when senior officials broke their silence in conversation with reporters from TV network ABC.

“The bureau will address not only the current threats we face today in cyber space, outer space, critical infrastructure, and through the misuse of disruptive technology like AI and quantum, but those we will face in the decades ahead,” State Department principal deputy spokesperson Tommy Pigott told ABC News.

Led by career diplomat Anny Vu, the Bureau ultimately reports to the under secretary for arms control and international security Thomas DiNanno, and will contain five distinct offices covering cyber security, critical national infrastructure (CNI), disruptive technology, space security, and threat assessment.

Officials told ABC they would be heavily focused on the activities of the so-called Big Four nation-state threat actors – China, Iran, North Korea and Russia – as well as international terrorist organisations.

The network additionally reported that the State Department has not revealed any details pertaining to the Bureau’s budget, staffing levels, or how it will work alongside the multiple pre-existing US agencies that claim some degree of expertise on cyber security matters – such as the Cybersecurity and Infrastructure Security Agency (Cisa) and the National Security Agency (NSA).

Engagement

Absent further detail at this stage, for the time being security leaders should continue to try to work with their existing US government contacts, said Xcape Inc board member David Small.

“Security leaders should prioritise maintaining relationships with Cisa, which remains the operational bridge between the State Department’s diplomatic goals and the private sector’s technical defence needs,” he said.

“Hiring a fleet of cyber security experts into the State Department is a bit like asking a career diplomat to debug a kernel panic; they’ll handle the negotiations beautifully, but the system is still going to crash.”

The appointment of three long-standing diplomatic experts as its leadership suggests the Bureau’s output will initially lean towards sanctions and treaty-writing, as opposed to technical remediation, he said.

As the new organisation beds in, Small said the business impact for private sector security pros was a period of increased regulatory noise as it attempts to define international security norms that may not always align with current engineering realities.

“To prepare, defenders and policy leaders should look to engage with the Bureau’s Office of Disruptive Technology early, treating it as a primary channel for informing the government on the feasibility of proposed AI and space-asset regulations,” added Small.

Suzu Labs senior director for secure AI solutions and cyber security, Jacob Krell, said that in his view, the Bureau of Emerging Threats was named for threats that have long-since emerged.

“Cyber and space capabilities served as the opening instruments in the current campaign against Iran. AI driven systems are compressing military decision cycles from days to minutes. These are the primary tools of state power being deployed right now by every adversary this bureau names. Standing up a bureau to address them through foreign policy is a recognition that the nature of conflict has fundamentally changed,” he said.

“That recognition is what makes the placement under the under secretary for arms control and international security significant. The United States is formally treating cyber, AI, and space as part of the same strategic conversation as conventional and nuclear capabilities. That is the right instinct.”

But like Small, Krell said he saw challenges ahead, in that technologically-driven conflict occurs much quicker than diplomats can handle. For the Bureau to be effective, he said it would need to operate at a pace reflecting technological reality, not at the pace of the State Department.

“The mandate is sound and the recognition is overdue. What matters now is whether this bureau arrives with the resourcing and operational speed to match threats that have already moved well past the planning stage,” he said.



Source link

Continue Reading

Trending