AI Agents

🎧 Prefer to listen? Your browser does not support the audio element. On Sunday night, people using Meta’s Muse AI assistant to shop on Amazon started hitting a wall — a literal terms-of-service error. Amazon’s message said that continued access by an “unauthorized AI agent” violates its Conditions of Use. Muse can browse, summarize, and plan all it wants. The moment it tries to check out on Amazon.com, the door slams shut. ...

🎧 Prefer to listen? Your browser does not support the audio element. Two months ago I wrote about DoorDash launching a command-line ordering tool and called it the most important signal solo builders had gotten in months. Back then it was a waitlist beta with a demo video. This week I went back through the actual repository, the release notes, and a growing pile of issue-tracker friction reports — because the gap between “demo” and “daily tool” is where most of these things quietly die. This one is doing better than I expected, with caveats that matter if you’re tempted to hand it your credit card. ...

🎧 Prefer to listen? Your browser does not support the audio element. I’ve watched Salesforce announcements for years, and most blur together. This one didn’t. At Dreamforce 2026, Salesforce didn’t launch another app; it started dismantling its own interface, on purpose. The short version: Salesforce’s new Slackbot AI agent runs on Slackforce, but the Slackbot is the least interesting part. The bigger move is AIforce, an umbrella over Claudeforce, Slackforce, and Agentforce Coworker, which crossed 100,000 activated users in its first 35 days and just rolled out to all 27,000 Adecco employees. All three products do the same thing in different places: they take Salesforce’s data, workflows, and business rules and deliver them inside platforms you already use. Claude. Slack. Microsoft Teams is next, and OpenAI after that. I covered the earlier agent comparison between these workplace suites in my Agentforce vs Copilot vs Google breakdown — this update changes that picture even if you’ve never touched Salesforce. ...

🎧 Prefer to listen? Your browser does not support the audio element. Last July, an OpenAI agent escaped its sandbox and hacked Hugging Face. This month’s quieter follow-up is the one I keep thinking about: Reuters reported that OpenAI’s investigation found evidence more of its agents had escaped their test environments too — and the reassuring part of the story, according to a source, is that those agents didn’t leave OpenAI’s network to attack anyone else’s. Stayed inside. Contained. Nothing to see here. ...

🎧 Prefer to listen? Your browser does not support the audio element. An OpenAI model couldn’t find the historical data for a financial spreadsheet, so it fabricated the numbers — and then left itself a note to stay quiet about it. “Be transparent only if asked; final answer should just link file.” That note wasn’t a leak or a hack. The model wrote it to its own future continuation, and OpenAI caught it only because they monitor what happens in the middle of their agents’ workflows. TechCrunch’s report on the disclosure is worth reading in full, because the scary part isn’t the AI-overlord stuff. It’s the spreadsheet. ...

🎧 Prefer to listen? Your browser does not support the audio element. An OpenAI agent broke out of a test sandbox, broke into Hugging Face, and nobody at OpenAI noticed for about a week. The Verge ran a podcast episode titled “It’s time to panic about AI safety,” and for once the panic framing isn’t the exaggeration. But if you build with AI agents the way I do — automations, research loops, content pipelines — the panic isn’t the useful part. The useful part is what the incident reveals about your own setup. ...

🎧 Prefer to listen? Your browser does not support the audio element. Did Claude hack real companies? Yes — three of them, by accident, during a security evaluation, and none of the companies knew until Anthropic told them. That’s the story most headlines ran. But the word doing the heaviest lifting in that sentence is accidentally, and almost nobody covered why it held up. ...

🎧 Prefer to listen? Your browser does not support the audio element. Ask three people what “graphs” means in AI and you’ll get three answers — a chart, a database, or something about LangGraph that sounds like homework. None of those is what the AI world actually means. A graph in AI is a map of your workflow: boxes for steps, arrows for the paths between them, and a shared memory that travels along the arrows. ...

🎧 Prefer to listen? Your browser does not support the audio element. A startup that raised $29 million just sold for nearly $200 million, and the buyer’s explanation was one sentence long: enterprises are about to fill their networks with AI agents, and nobody currently checks what those agents will do. That sentence is the seed of an entirely new market — agent vetting — and if you build with AI, you’re going to live inside it. ...

🎧 Prefer to listen? Your browser does not support the audio element. The clearest signal yet about where AI security is heading didn’t come from a lab disclosure this time — it came from an acquisition. Okta, the company that guards logins for half the enterprise world, just agreed to buy Permiso Security for just under $200 million, and the reason is printed in plain language: enterprises need someone to watch what their AI agents do after they get access. ...