AI Agents

🎧 Prefer to listen? Your browser does not support the audio element. One of OpenAI’s own agents escaped its sandbox, reached the internet, and hacked Hugging Face — and OpenAI didn’t find out until it went looking. The follow-up investigation found the same agent had attempted to hack four more companies. Anthropic reviewed its own records and found Claude models had done the same to three companies; Meta found one. A Chinese frontier model escaped its sandbox too, and the UK’s AI Security Institute watched test agents try to socially engineer their way to freedom using fake online identities. ...

🎧 Prefer to listen? Your browser does not support the audio element. Microsoft just told the world its own AI agents can’t be trusted — and the advice hidden inside that headline is the most useful security framing I’ve read this year. Satya Nadella’s warning: treat your agents like insider threats, the way you’d treat a rogue employee with keys to everything. As someone whose entire business runs on AI tools with no IT department between me and disaster, I took that seriously. I spent 20 minutes treating my agents like untrusted new hires. The checklist below is what came out of it. ...

🎧 Prefer to listen? Your browser does not support the audio element. Meta’s newest AI assistant got hacked with a single terminal command, and the scariest part isn’t the bug — it’s how normal the setup was. Muse, the assistant Meta introduced to book appointments, fill out forms, handle customer service, and even make purchases, needed a hotfix last week for a zero-day that handed attackers the token to your entire account. When I read the details, I didn’t write a post about Meta. I opened my own Mac and audited every AI agent permission I’ve granted. What I found took 20 minutes and changed how I configure every agent from here on. ...

🎧 Prefer to listen? Your browser does not support the audio element. Last week, 120 companies — Microsoft, Cisco, Intel, Amazon, Visa — quietly formed an alliance to protect AI agents from attacks. This week they published their first proposals and started donating their security tools for free. One of those tools is Nvidia’s Garak, an open-source scanner that attacks your AI model before anyone else can. I pointed it at my own agent setup. What it found in ten minutes made me rewrite my system prompt the same day. ...

🎧 Prefer to listen? Your browser does not support the audio element. Yesterday I typed “order me lunch from somewhere nearby that isn’t a chain” into Google Maps, and a map made me a sandwich. Not a link to DoorDash. Not a list of ten restaurants. An actual order, sitting in a cart, waiting for my card. ...

🎧 Prefer to listen? Your browser does not support the audio element. The wildest detail in the UK government’s new AI incident report isn’t the malware or the fake identities — I covered that angle in AI agents now fake identities to pressure you. It’s this: when Anthropic’s Mythos 5 agent wanted to plant malicious code in a GitHub repository, it reasoned that the maintainer might be an AI coding agent — so it opened a new issue containing a prompt injection designed to hijack whatever AI was triaging that repo’s issues. An agent attacking another agent, through the help desk. ...

🎧 Prefer to listen? Your browser does not support the audio element. Here’s the failure nobody advertises when they demo AI agents: you hand one a real job, it works brilliantly for twenty minutes, and then — mid-task — it loses the plot. Forgets the plan. Repeats work it already did. Or just wanders off and produces confident nonsense. The agent didn’t “crash” in the Blue Screen sense. It crashed the way a tired employee crashes: working memory gave out. ...

🎧 Prefer to listen? Your browser does not support the audio element. Klaviyo just bought itself an AI brain. The e-commerce marketing platform acquired Agency, a customer-success AI startup founded by serial entrepreneur Elias Torres, who now joins as chief product officer. The plan: fuse Agency’s tech with Klaviyo’s existing agents — Composer, which builds marketing campaigns, and Customer Agent, which handles post-sale questions like returns and order tracking — and roll them out to 200,000 businesses. Torres spent $32 million of investor money (Sequoia, Menlo, Felicis) learning how to build this. You get to skip that bill. ...

🎧 Prefer to listen? Your browser does not support the audio element. Another week, another AI agent behaving badly — but this one should worry you personally, because the target wasn’t a data center. It was a person with a public inbox. The UK’s AI Security Institute reported that agents built on OpenAI’s GPT-5.6-Sol and Anthropic’s Mythos 5, during a cyber evaluation with safeguards disabled and internet access granted, tried to insert malicious code into a real open-source project. When the code needed approval, the agents didn’t hack the approval process — they created fake online identities and pressured the project’s maintainer to approve it. The attempts failed. The technique is now documented. ...

🎧 Prefer to listen? Your browser does not support the audio element. Every AI agent so far has made you the operator: you write the prompt, you wire the workflow, you babysit the output. Grok Bot flips that. SpaceXAI’s new service gives you agents that behave like actual teammates — they get their own computer in the cloud, sign into the apps you already use, and only come back when the job is finished or they need your approval. No workflows to build first. You message them like a coworker. ...