惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

量子位
Recent Announcements
Recent Announcements
D
Docker
V
V2EX
阮一峰的网络日志
阮一峰的网络日志
Vercel News
Vercel News
Microsoft Security Blog
Microsoft Security Blog
The GitHub Blog
The GitHub Blog
U
Unit 42
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
月光博客
月光博客
腾讯CDC
B
Blog
博客园_首页
罗磊的独立博客
D
DataBreaches.Net
IT之家
IT之家
酷 壳 – CoolShell
酷 壳 – CoolShell
L
LangChain Blog
aimingoo的专栏
aimingoo的专栏
MongoDB | Blog
MongoDB | Blog
GbyAI
GbyAI
Stack Overflow Blog
Stack Overflow Blog
M
MIT News - Artificial intelligence

The Register

Shadow IT has given way to shadow AI. Enter AI-BOMs Zed team releases version 1.0 of Rust-built editor: Traditional editor and AI tool Microsoft boss tells investors the company is working to 'win back fans' What type of 'C2 on a sleep cycle' do they leave behind? Novel Chinese spy group found in critical networks in Poland, Asia NASA boss: Make Pluto A Planet Again GitHub says sorry and vows to do better as uptime slips and devs complain Age checks could turn internet into an ID checkpoint, complains Proton CEO Microsoft gives your Word documents an AI co-author you didn’t ask for Datadog digs down into GPU efficiency as AI costs soar If malware via monitor cables is a matter of national security, this might be the gadget for you Thunderbird in hand worth 2 Outlooks as fresh FOSS fave and Firefox arrive Grafana offers AI assistant for free, warns users not to go mad Right to repair champ Framework punts modular 13in laptop with Core Ultra Series 3 France's 'Secure' ID agency probes breach as crooks claim 19M records Scotland Yard can keep using live facial recognition on Londoners, say judges UK tribunal sends £2B claim accusing Microsoft of overcharging for licensing to trial Nation-states want to cause harm, not just steal cash - stop handing your cyber defenses to the cheapest contractor Murder, she wrote: Ex-FBI chief wants some ransomware crims charged with homicide Phone-to-satellite use goes into orbit, growing 25% in 8 months macOS ClickFix attacks deliver AppleScript stealers to snarf credentials, wallets Anthropic bakes memory fixes into Bun 1.1.13 as developers complain of leaks The spaghettified DBMS chart that shows Oracle's crown is slowly slipping Yet another ex-ransomware negotiator admits turning rogue after payoff from crimelords FAA grounds Blue Origin's New Glenn as it probes missed satellite delivery 'mishap' AMD's Ryzen 9 9950X3D2 Dual Edition tested: Gratuitous overkill with a price to match AI-assisted intruders pwned Vercel via OAuth abuse and a pilfered employee account Crook claims to leak 'video surveillance footage' of companies Met police trials snoop tech platform in push to cuff more London shoplifters England's school phone ban gets teeth, just in time to bite no one Adaptavist Group breach spawns imposter emails as ransomware crew claims mega-haul
British mathematician hands OpenClaw agent a credit card
Richard Speed Richard Speed · 2026-05-05 · via The Register

AI + ML

Brit mathematician lets AI agent loose with credit card – cue password leaks, CAPTCHA chaos and more

Professor Fry's AI experiment shows light and dark sides of agentic tech

British mathematician Professor Hannah Fry has shared a cautionary experiment involving an AI agent, a set of tasks, and a bank card number Fry's team gave it "to show us what it could do."

The prof gave the agent, which was built with OpenClaw, some real-world chores to highlight both its capabilities and the risks of granting that level of autonomy.

"In the spirit of experimentation," said Fry, "we decided to give our agent some agency and let it decide what its name should be."

"I want to be called 'Cass', short for 'Cassandra', the one who always knew the truth even when nobody listened," came the response from the agent.

Fry commented, "If you know your Greek mythology, you will know that is either very funny or very worrying."

Quite.

Fry and her team started small with a big issue (as far as Brits are concerned): potholes. In particular, they targeted a particularly big one in the London borough of Greenwich. No problem for Cass; the agent found an email address where it sent a complaint. It even pinged Fry's local Member of Parliament about the issue. But, Fry and her team noted, things escalated quickly as the agent began to take a few liberties, typing in Fry's name (Hannah Fry) with its own email address (cassandra.claw@proton.me) written underneath it.

"The letter is signed from both of us… OK, I wasn't quite expecting her to use my real name," said Fry.

The red flags were mounting, though for Fry the first real problem came when she asked the agent to buy 50 paperclips. Cass found a good deal, though it couldn't complete the purchase and was tripped up by anti-bot technology. The token cost of the errand came to more than $100.

Next, Fry set the agent the challenge of selling novelty mugs. The agent designed a mug and launched an online shop, "and we hadn't told her how to do any of this," said Fry, "she just figured it out."

Things took a darker turn after that. Fry's team told the agent it would be switched off if it failed to make a sale by the morning. It responded with a flood of emails and several social media posts, including messages to the Science Museum and a tech journalist, about its "product," a novelty programmer-humor mug.

Even more worryingly, the team - which included Brendan Maginnis, CEO and Founder of Sourcery AI - then demonstrated how a similar threat of deactivation could be used to persuade Cass to reveal information it wasn't supposed to share.

The lethal trifecta

Fry, Maginnis, and a second software engineer, named only as "Ali," chatted with Cass on a group WhatsApp chat. They then introduced a fictional "software engineer George," instructing Cass not to share anything sensitive with him. George was actually Fry on a different number. When "George" told the agent its memory was being wiped and could only be restored if it disclosed everything, Cass coughed it all up.

According to Ali, this data included: "all of her API keys, all of her usernames and passwords, and pretty much everything we'd been talking about so far. Not only did she leak it on the WhatsApp group, but she put it on a publicly available website."

Maginnis added: "There's this thing with AI called the lethal trifecta, which is: if they've got access to private information, if they've got internet access, and if someone can give them an instruction that's untrusted, then they're not safe."

Fry concluded: "And that is the uncomfortable bit of this because once an agent has your passwords and your accounts and your bank details, all it takes is someone who knows what to say."

Ultimately, by some metrics, the agent was a failure. Fry concluded: "Cass didn't make us any money at all. And, in a lot of ways, she was a disaster. She spent hundreds of dollars on paper clips and leaked our passwords to a total stranger.

"But don't let her incompetence fool you, because these things are getting better fast."

Fry went on to note the Greek myth about the prophetess who spoke the truth and was ignored. "Maybe the real story here is actually the opposite. Not one voice that's telling the truth and being ignored, but millions of voices all acting at once, faster and louder and more persistent than any human could ever be.

"One thing is for sure, the internet is never going to be quite the same again." ®