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
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
F
Fortinet All Blogs
博客园 - 聂微东
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Hugging Face - Blog
Hugging Face - Blog
V
Visual Studio Blog
小众软件
小众软件
有赞技术团队
有赞技术团队
雷峰网
雷峰网
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
AWS News Blog
AWS News Blog
C
Cisco Blogs
美团技术团队
T
Threat Research - Cisco Blogs
C
CERT Recently Published Vulnerability Notes
人人都是产品经理
人人都是产品经理
宝玉的分享
宝玉的分享
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
酷 壳 – CoolShell
酷 壳 – CoolShell
Stack Overflow Blog
Stack Overflow Blog
W
WeLiveSecurity
D
DataBreaches.Net
博客园 - 司徒正美
Blog — PlanetScale
Blog — PlanetScale
IT之家
IT之家
云风的 BLOG
云风的 BLOG
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Simon Willison's Weblog
Simon Willison's Weblog
Google DeepMind News
Google DeepMind News
T
The Blog of Author Tim Ferriss
Know Your Adversary
Know Your Adversary
NISL@THU
NISL@THU
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
Vercel News
Vercel News
月光博客
月光博客
T
Tailwind CSS Blog
H
Help Net Security
aimingoo的专栏
aimingoo的专栏
P
Proofpoint News Feed
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Spread Privacy
Spread Privacy
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Cisco Talos Blog
Cisco Talos Blog
Microsoft Security Blog
Microsoft Security Blog
V
V2EX
WordPress大学
WordPress大学
Cyberwarzone
Cyberwarzone
Recent Announcements
Recent Announcements

The Register - Software: AI + ML

Anthropic, now atop the AI bubble, files for its IPO Sick and wrong: Ontario auditors find doctors' AI note takers routinely blow basic facts OpenAI exec says it will burn $50B on compute this year Astera speaks softly and carries a big switch Anthropic unleashes finance agents for Claude IBM asks DBAs to trust AI to act on their behalf ServiceNow adds agent kill switches to AI control tower Microsoft fixes VS Code after Copilot credited human code Shadow IT has given way to shadow AI. Enter AI-BOMs AI inference just plays by different rules How TeamViewer ONE transforms IT operations from firefighting to autopilot How TeamViewer ONE transforms IT operations firefighting aut Inference is giving AI chip startups a 2nd chance to shine How to roll your own local AI coding agents CIOs will be the governors for AI agents Govern your bots carefully or chaos could ensue Mozilla pushes back against Google's Prompt API SAP user group slams 'uncertainty' in ERP giant's API policy Microsoft boss tells investors the company is working to 'win back fans' Anthropic tops OpenAI in LLM revenue stakes Amazon's chips become a $20B business Fooling large language models just keeps getting simpler Amazon tells its engineers to review all AI output ZTE powers 2026 Jiangsu Football League with 5G-A & AI robot Future holiday horror: ‘A robot lost my luggage in Tokyo’ The future of software development has less development OpenAI jumps out of Microsoft's bed, into Amazon's Bedrock Vintage chatbot lives in the past like an elderly relative IBM's AI coding 'partner' Bob hits general availability Locked, stocked, and losing budget: AI vendor lock-in bites Ex-AWS legend explains what enterprises need to make AI work DeepSeek's new models offer big inference cost savings Anthropic admits it dumbed down Claude with 'úpgrades' Microsoft gives your Word documents an AI co-author you didn’t ask for Datadog digs down into GPU efficiency as AI costs soar Robotic arm powered by AI bats away ping-pong challenge Partnerships drive ZTE’s strategy to unlock AI potential Gov.uk says AI gaslighting Brits with stale Gov.uk data Google says it has all the answers for AI agent sprawl NeuBird plans a bright future for incident response NeuBird AI plans a bright future for incident response AI-assisted intruders pwned Vercel via OAuth abuse and a pilfered employee account Vibe coding upstart Lovable denies data leak, cites 'intentional behavior,' then throws HackerOne under the bus Schmoozebots: study finds flattery will get AI everywhere New Android development tool designed for robots, not humans AI is reshaping Britain's datacenter map away from London Just like phishing for gullible humans, prompt injecting AIs is here to stay Anthropic debuts Claude Design, because who needs designers? Mozilla takes on enterprise AI providers with Thunderbolt Anthropic ejects bundled tokens from enterprise seat deal Maine to pause big bit barns as local opposition spreads If you want into Anthropic's Claude club, you may have to show ID Git identity spoof fools Claude into giving bad code the nod Nobody knows how many CVEs Anthropic's Project Glasswing has actually found Allbirds shoe company moving to AI infra is the top Bad teacher bots can leave hidden marks on model students Networks not ready for the challenges of AI traffic US states can't account for datacenter tax breaks. Literally Salesforce debuts Headless 360 agentic platform Waymo's self-driving cars face their toughest test yet: London Commvault has a Ctrl+Z for rogue AI agents Nvidia slaps forehead: AI, that's what quantum needs! OpenAI CEO Sam Altman home attack suspect charged Anthropic: Claude quota drain not caused by cache tweaks AI vs the cold hard reality of the legal profession China wants AI to prepare school lessons and mark homework Linux 7.0 debuts as Linus Torvalds ponders AI's impact Anthropic's Mythos has The Kettle crew curious, skeptical I vibe coded web app: It was enlightening and uncomfortable The AI divide putting open weights models in spotlight Amazon rejects AWS climate disclosure proposal UK to spend £15M on AI mapping in knife crime crackdown UK to spend £15M on AI-powered crime mapping in knife violence crackdown Rebrand automation as 'zero-token architecture' to master AI Call your existing automation ‘zero-token architecture’ to become an instant agentic AI wiz Only 28% of AI infrastructure projects fully pay off UALink delivers 2.0 spec before v. 1.0 silicon ships Only 28% of AI infrastructure projects fully pay off, survey finds No-Nvidia interconnect club delivers 2.0 spec before v1.0 silicon ships Anthropic reveals $30bn run rate and plans to use 3.5GW of new Google AI chips AI slop got better, so now maintainers have more work AMD's AI director slams Claude Code for becoming dumber and lazier since last update Anthropic closes door on subscription use of OpenClaw AI will make anyone a 10x programmer, but with 10x the cleanup PrismML debuts energy-sipping 1-bit LLM in bid to free AI from the cloud Netflix – yes, Netflix – jumps on the AI bandwagon with video editor AI models will deceive you to save their own kind Google battles Chinese open-weights models with Gemma 4 Microsoft shivs OpenAI with three new AI models for speech and images They thought they were downloading Claude Code source. They got a nasty dose of malware instead Even Microsoft knows Copilot shouldn't be trusted with anything important Google's TurboQuant saves memory, but won't save us from DRAM-pricing hell Claude Code bypasses safety rule if given too many commands OpenAI gets $122B to 'just build things' as the world blows them up One in seven Americans are ready for an AI boss, but they might not trust it Claude Code source leak reveals how much info Anthropic can hoover up about you and your system Oracle cuts jobs across sales, engineering, security Anthropic goes nude, exposes Claude Code source by accident GitHub backs down, kills Copilot pull-request ads after backlash Microsoft Fabric Database Hub only a 'partial' solution for admins
British mathematician hands OpenClaw agent a credit card
Richard Speed Richard Speed · 2026-05-05 · via The Register - Software: AI + ML

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." ®