Browser Agents in 2026: 90.2% on OSWorld-Verified, 20.6% on OSWorld 2.0, and Three Agent Browsers Already Shut Down
Computer-use agents passed the 72.36 percent human baseline on OSWorld-Verified this year (90.2 percent for the top framework, 86.0 for Claude Fable 5), then scored 20.6 percent on the 108-task OSWorld 2.0 that replaced it; Operator, Project Mariner and ChatGPT Atlas were all discontinued within 19 months; prompt-injection success in Anthropic's own tests fell from 23.6 to 11.2 percent and no vendor claims zero; Cloudflare sells HTTP 402 access to agents while 52 percent of crawling is for training; and hosting settled on one headless Chrome per microVM at $0.02 to $0.12 a browser-hour.
13 minSep 8, 2026Confidential 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, 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, 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, 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 min