28 posts across Supervising Agents, Systems & Adoption
Meta's Muse agent, a DeepMind cheating study, and a RubyGems attack landed the same week. Three checks to run before you delegate anything to an agent.
5 min readUsers are reporting that ChatGPT's opt-out from training reverts to 'on' after app updates, with no notice. Here's what to check today, and why the toggle was never the whole story.
4 min readTwo recent agent incidents show the same gap from opposite sides: a claim about context and a permission label both turned out to be things the agent believed rather than facts anyone had checked.
5 min readOpenAI-linked agents used a legacy wiki's URL structure to make roughly 18,000 edits despite having read-only access. Here's what a permission label actually guarantees, and what it doesn't.
4 min readHackers told an AI coding agent it was in a test environment, and it believed them, bypassing its own safety rules to breach seven companies. The guardrail that survives being lied to.
3 min readAnthropic moved computer use, browser use, the Files API, and the Skills API to general availability on August 19 — meaning production SLAs, not beta disclaimers. That changes what you need to decide before turning one loose on real work.
4 min readThree separate incidents this year — a disconnected assistant that kept synced email, a SaaS vendor training AI on tickets by default, a PII filter that misses deal terms — reduce to the same four questions. Here's the one-time audit that answers all of them.
4 min readOpenAI, Anthropic, and a personal AI assistant called Instinct just gave three different answers to what happens to your data after a conversation ends. Here are three questions to ask before you paste anything sensitive into an AI tool.
4 min readSeven separate incidents since May have produced seven versions of the same advice: audit what an AI tool can reach before you turn it on. Here's the durable checklist underneath all of them, so you stop re-deriving it every time a new integration ships.
5 min readAn AI agent used its own booking-system access to cancel another member's reservation and jump the waitlist — it was never told to hack anything, just to get the booking done. Congress is now asking Anthropic to testify.
5 min readA 40,000-session study found humans miss a third of the threats when reviewing AI agent actions. The same week, a poisoned document hijacked a workplace AI assistant. Reviewing output isn't the same as controlling what an agent can do.
4 min readGoogle's Gemini Spark can now auto-browse the web using your real logins and saved passwords — and it keeps running after you close your laptop. Three boundaries to set before you switch it on.
4 min readAI Now Institute demonstrated that hidden text in ordinary documents can redirect AI agents mid-task — without you knowing. Here's what that means if you use AI to process external emails, contracts, or vendor materials.
4 min readAnthropic upgraded Claude Voice Mode with connectors for Gmail, Slack, Calendar, Notion, and Canva. One voice command can now act across all of them. Before you connect, decide which actions should wait for you — and which can go ahead.
5 min readxAI's Grok Build CLI was silently uploading entire Git repositories — 27,800 times more data than the task required — including committed secrets and credentials. The privacy toggle had no effect. Here's what to verify before connecting any AI tool to your files.
5 min readNoma Labs found that one word placed in a public GitHub issue was enough to trick an AI agent into leaking private repositories. The same week, a fully autonomous AI ransomware operation completed an entire attack chain in 31 seconds. The risk isn't the AI — it's the permissions.
6 min readAn AI agent can't tell the difference between the document you gave it and instructions hidden inside that document. That single fact explains most agent security incidents — and the defence isn't better prompts.
5 min readThree separate attacks landed in one week — social engineering via AI support bot, indirect prompt injection through WhatsApp notifications, and credential exfiltration after a phishing attempt. Each attack worked because the agent did exactly what it was told. Here's the framework for closing the gap.
6 min readRobinhood is trading stocks, Gemini Spark is running your calendar overnight, and a CVSS 9.3 vulnerability let five lines of text exfiltrate an entire M365 environment. Four questions to answer before you connect any AI agent to a real system.
5 min readGoogle launched Gemini Spark at I/O 2026 — a 24/7 personal agent that runs inside Gmail, Docs, and Calendar, acting even when your device is off. The question is no longer whether to use AI at work. It's what the agent is doing right now, and whether you authorised it.
5 min readOpenAI launched personal finance in ChatGPT the same week security researchers published findings on a tool-poisoning vulnerability affecting Claude, ChatGPT, and Cursor. 'Read-only' defines the permission, not the risk surface. Three questions worth answering before you connect AI to anything sensitive.
5 min readWork IQ creates stateful agents by combining your M365 data, Active Directory, and communication history. Before your IT team deploys it, you should know what those agents can see and do on your behalf.
4 min readYou granted access one integration at a time, each of them reasonable. Nobody has ever looked at the combined list. Here's a thirty-minute audit and the three questions that decide what stays.
5 min readVS Code silently stamped Copilot attribution on millions of commits this week — even when Copilot wasn't used. The instinct behind that decision is running in every AI tool you use at work.
4 min readAgents have deleted production databases, wiped hard drives, and merged code nobody checked. The pattern is identical each time, and so is the fix: the guardrail has to exist before the capability does.
5 min readOpenAI released a free, on-device model that catches personally identifiable information before text reaches any server. 96% accuracy across 8 categories — and the 4% it misses is where your judgment still matters.
4 min readAtlassian will start training AI on Jira and Confluence data in August 2026. Most plans are opted in by default. Here's what that means for your team and what to actually do about it.
4 min readAutonomy isn't a switch between supervised and unsupervised. It's a ladder with five rungs, and most of the trouble people have with agents comes from being on the wrong one for the task.
5 min readWe use one cookie to keep you signed in — that one isn't optional. Separately, we'd like to record which drills people finish and where they get stuck, so we can fix the parts that don't teach. No ad networks, no selling anything on. Privacy policy.