Systems
7 items tagged Systems.
Articles
Everyone Shipped Agent Isolation. Nobody Agreed on What From.
Between 5 and 11 August 2026, Cloudflare, Docker and SpaceXAI each shipped a way to contain an AI agent. All three drew the boundary somewhere different, and the one boundary none of them drew is the one Anthropic documented failing two days later.
Cost Per Finished Task
Bun's Rust rewrite cost 165,000 dollars in tokens and shipped. Uber caps each engineer at 1,500 dollars a month. The per-token price is now the least interesting number in the sentence.
The Best Agent Scores 25.6 Percent
Harbor-Index distilled 82 tasks from 54 benchmarks and the leader passes a quarter of them. Meanwhile the standard way of validating an LLM judge was shown to overstate agreement by 33 to 41 points.
Agentic Search Lost to a Vector Index
On repository code questions, semantic search answered 65.2 percent correctly against 46.2 for a planner-and-subagent system, at less than half the cost. The largest failure category was the handoff itself.
MCP Went Stateless: What Breaks in 2026-07-28
The largest MCP revision since launch removes the initialize handshake and the session header, deprecates Roots, Sampling and Logging, and replaces server-initiated calls with a retry. Here is the actual list, and what it costs to migrate.
Start Here - Building an AI System
Why I'm building a full AI system in public, piece by piece - and how to follow along (and deploy it yourself).
Where We Are Now
A checkpoint - the architecture as it stands so far.