Confidential Computing for AI in 2026: Apple Moved to Google's TEEs, a $1,000 Interposer Broke the Keys, and Firecracker Still Can't Do It
What a hardware enclave actually promises for an AI workload, what it costs (4 to 28% depending on what you measure), what broke it this year (TEE.fail, Battering RAM, WireTap), who runs inference in one (Apple, Google, Meta, a dozen startups) and who doesn't say (OpenAI, Anthropic). Plus the state of SEV-SNP, TDX and Arm CCA in the kernel, why my microVM platform cannot offer it yet, and the commands to verify an attestation yourself.
15 minSep 3, 2026Top AI Agent Sandbox Providers: An Engineer's 2026 Roundup
A working engineer's roundup of the top AI agent sandbox providers: isolation, hosting, persistence and pricing compared — including the one I built myself.
10 minSep 3, 2026AI Agent Sandboxes: What They Are and How to Choose One
What an AI agent sandbox is at the systems level, the four properties that decide one, and how 15 platforms compare — from an engineer who built one of them.
10 minSep 3, 2026AI Agent Sandbox Runtime: The Six Options and Who Uses Them
Firecracker, gVisor, Kata, containers, V8 isolates and libkrun compared — how each isolates, what it costs in memory, and which sandbox vendors run it.
10 minSep 2, 2026What Scale to Zero Cost Me to Build: 50s Sleeps, 14s Wakes
Hibernate took 50 seconds. Wake took 14, not the 1.3 I had reported. The measured price of building scale to zero on a Firecracker fleet, and every fix.
9 minSep 2, 2026Sandbox Creation Time Benchmarks Measure Different Things
Every AI sandbox matrix has a creation time column spanning 0.79ms to 2.7s. That spread is definitional, not performance. Here's how to make it comparable.
10 minSep 2, 2026Isolation Is Not an Abuse Control: Lessons From My Fleet
A free-tier signup mined crypto on my microVM fleet in 27 minutes. Containment held perfectly and it changed nothing. What I built afterwards, in what order.
9 minSep 2, 2026microVM Production Incidents: 4 Postmortems From My Fleet
Four real postmortems from a multi-tenant Firecracker microVM fleet I run solo: a wiped boot disk, silent config drift, a fatal page fault, and no alerts.
10 minSep 2, 2026Firecracker microVM Cloud, Built Solo in 6 Months: 179ms Boots
What it actually takes to run a Firecracker microVM cloud alone: snapshot-restore on every create, 179ms boots, pre-allocated netns, and the real costs.
9 minSep 2, 2026I Measured Every Stage of My 179ms Firecracker Boot Path
Where every millisecond of a Firecracker create goes, measured on my own production fleet, plus why I refuse to stop the clock before the guest answers.
9 minSep 2, 2026My Fork Docs Were Wrong: What VM Forking Really Preserves
I shipped a doc claiming forks keep processes and open files. A smoke test proved otherwise. Three fork paths measured, and the five places each breaks.
10 minSep 2, 2026Container vs microVM vs gVisor: Choosing Agent Isolation
A practical guide to picking an isolation model for AI-agent code execution, from someone who runs a Firecracker fleet: five models, five axes, one table.
9 minSep 2, 2026Checkpoint Restore Implementation: What It Cost Me to Build
Analysts call checkpoint/restore table stakes by 2027. Here is the real bill: snapshot storage, userfaultfd lazy restore, and a 50s hibernate vs 1.2s wake.
9 min