Articles

Research and analysis on AI agent safety, infrastructure, and the tools agents need to operate reliably in the real world.

---

Developers Are Grieving

Software engineers all over the world are going through real, unvarnished loss. We map the Kübler-Ross stages — denial, anger, bargaining, depression, acceptance — onto what’s happening in the profession right now, name a sixth stage of finding meaning, and explain why this grief is harder than most: the thing causing the loss is also the thing devs are being asked to embrace, daily, in their workflow.

Markdown Is the Lingua Franca of AI

A format one guy made for his blog now mediates communication between humans and the most powerful AI systems ever built. We trace how Markdown became the universal interchange format for AI — from training data prevalence and token efficiency to the agent instruction layer and the self-reinforcing cycle that locks it in.

Your Keys, Their Server

A Python package stole everything on your machine. We break down the LiteLLM supply chain attack step by step — how attackers cascaded through Trivy to poison a package downloaded 3.4 million times per day — and explain the structural changes that actually reduce your exposure: fewer secrets on your machine, device-bound credentials, short-lived tokens, and anomaly monitoring.

Most MCPs Should Be CLIs

MCP is everywhere — but a growing number of serious agent builders are reaching for CLI tools instead. We walk through the first-principles argument: context windows are finite, MCP’s token overhead is 4–32x higher than CLI, reliability drops with network dependencies, and models already understand shell commands from training data. MCP wins for services without CLIs and multi-user auth — but for the common case, the evidence points to CLI.

More Agents Than Humans

There will be more AI agents in the world than humans. We walk through the reasoning step by step: every digital tool proliferates beyond one-per-person, agents have no physical constraints, inference costs are falling 1,000x in three years, specialization drives the same multiplication that gave us 80 apps per phone, and the largest companies are already planning for 100:1 agent-to-human ratios. The question isn’t if — it’s how you run that many agents safely.