The AI security signal, not the noise.
Concise field notes on emerging threats, defensive patterns, and what's actually working — written for teams shipping AI in production.
Live from The Midway: Day-One Dispatch from the Autonomous Future Summit 2026
The Autonomous Future Summit kicks off today in San Francisco. Here's our on-the-ground dispatch from The Midway — the demos that landed, the conversations we're pulling into the hallway, and the security questions the mainstage keeps skipping.
Physical AI Red Teams: Five Attack Patterns We're Hunting on the Summit Floor
As the Autonomous Future Summit opens today in San Francisco, here's the working red-team playbook we're testing against robot foundation models, operator copilots, and fleet dispatch stacks — five attack patterns, each with a concrete detection signal.
Preview: The Autonomous Future Summit 2026 in San Francisco — and Why Physical AI Needs a Security Layer
On July 16, 2026, the robotics and physical-AI ecosystem lands at The Midway in San Francisco. We're heading in — here's the agenda we're watching, and how TrendGuru fits into a stack that is quickly moving from pixels to atoms.
Field Report: TrendGuru at The smarter E Europe 2026 in Munich
Three days on the floor at Europe's largest energy-industry alliance in Messe München — what we saw across solar, storage, e-mobility, and why AI security is quietly becoming a grid problem.
Securing the AI Behind the Battery: Notes on ACCURE Battery Intelligence at ees Europe 2026
ACCURE's analytics platform watches gigawatt-hours of battery storage in real time. We sat down at their ees Europe booth to talk about what happens when the models doing the watching become the target.
Bidirectional Charging Is a Software Problem: ABB E-mobility, V2G, and the Case for Backend Red-Teaming
ABB E-mobility's Power2Drive booth was built around bidirectional DC charging. Every V2G flow is also a new authentication and control path — and that's where we come in.
AI in the Trading Room: ADEX Energy, Virtual Power Plants, and the Adversarial Robustness Gap
ADEX Energy showed a live SaaS platform for RES forecasting, market trading and BESS optimization at EM-Power Europe. Every one of those modules is an AI agent with market access.
LLMs in Solar Due Diligence: A Conversation with Aevy at Intersolar Europe 2026
Aevy's Intersolar Europe booth showed an LLM pipeline that reads thousands of pages of solar asset-management documents. We talked about the failure modes nobody in the room was mentioning.
Prompt Injection in 2026: The New Perimeter Attack
Indirect prompt injection has quietly become the most exploited weakness in enterprise LLM deployments. Here's what changed and how to defend.
Autonomous AI Agents Are Expanding Your Attack Surface Faster Than You Think
Every agent that can browse, write files, or call an API is a new identity in your environment. Most orgs are not treating them like one.
Robotics + AI: Why Industrial Deployments Need a Different Threat Model
When the LLM is driving a forklift, 'hallucination' stops being a UX problem. Security patterns from the enterprise SaaS world don't transfer cleanly.
Deepfake Voice Phishing Is Now Cheaper Than SMS Spam
Cloning a colleague's voice from a 30-second LinkedIn video is a commodity. Executive impersonation calls are up 340% year over year.
You Cannot Secure Shadow AI You Have Not Inventoried
The average mid-market company runs 47 AI tools its security team does not know about. Discovery is now step zero of any AI governance program.
Model Supply Chain Attacks: The npm Moment for AI
Poisoned model weights on public hubs are the new typosquatted packages. What supply chain security taught us translates almost directly.