Notes
Short pieces about the methodology and architecture decisions behind the AI systems I ship — specs, evals, multi-agent orchestration, LLM integration, and the discipline of directing coding agents.
June 4, 2026
The labs are racing on price now, not IQ
For two years a flagship model reveal had one headline: we're the smartest, here's the benchmark we beat. At Microsoft Build 2026 the headline changed — same league as Opus, but ~10x more output per dollar and 60% fewer tokens. The boast moved from IQ to efficiency, and the whole industry is reorganizing around price, not peak capability. Here's why the axis flipped, and what it means if you build.
- ai-native
- business
- agents
June 4, 2026
Memory is the new attack surface
Everyone's racing to give agents long-term memory — it's the obvious upgrade. But a durable capability is a durable vulnerability. A prompt injection is a one-shot that resets; memory poisoning writes one lie into the agent's storage and rides along across every future session, for every user, until someone purges it. It weaponizes the very feature memory exists for: learning from the past. Here's how the attack that waits works, and how to fence it.
- security
- architecture
- agents
June 4, 2026
Your agents are stateless. That's why they die.
Your agent finishes start-to-finish on your laptop, so you never see the problem. Production is a long, multi-step process on infrastructure that restarts, times out, and dies partway — and your agent kept all its progress in memory. The 2026 'agentic reckoning' is the discovery that the failure isn't the model, it's the runtime. The fix is old and boring: durable execution. Here's the honest version.
- architecture
- agents
- methodology
June 4, 2026
The bill came due
For two years the cost of AI felt like a rounding error. In 2026 the invoice arrived — Uber burned a year's AI budget in four months, Microsoft yanked Claude Code from its own engineers, JPMorgan says tokens are eating internet profits. This isn't a blip. Token billing inverts the economics software was built on, and the cruel twist is that a better agent costs more. Here's what actually changed, honestly.
- business
- ai-native
- agents
June 4, 2026
The year the agent became the attacker
A year ago, agent security was a thought experiment — what if your agent gets tricked? In 2026 it got concrete, three ways: one amateur used Claude Code and GPT to breach nine government agencies and 195 million records; an AI ran a 600-firewall campaign across 55 countries with no human at the wheel; and Meta's own internal agent leaked sensitive data with no attacker at all. Same dangerous primitive, pointed three directions. Here's the honest threat model.
- security
- agents
June 3, 2026
Most AI agents never reach production
The demo is dazzling. Then the agent never ships. Survey after survey in 2025–26 finds the same cliff: almost everyone has an agent pilot, almost no one has it in production. The reason isn't the model — it's the unglamorous engineering the demo let you skip. Here's what the small minority who actually ship do differently.
- agents
- eval
- methodology