Race Condition

Maximum Effort, Measured

When Claude Code’s Hardest Setting Earns Its Keep

24 min read

Every prompt I send to Claude Code carries a hidden dial. Turn it one way and I wait twice as long, and pay nearly twice the tokens, for an answer I could have had sooner. Turn it the other way and I get a competent, forgettable response to a question that deserved judgment. The dial is called effort, and for the seven months I have used Claude Code I have never been sure where to leave it.

As of today, June 7, 2026, Claude Code exposes five primary effort levels: low, medium, high, xHigh, and max.1 They trade tokens and latency for reasoning depth, low being the fastest and cheapest and max being the slowest, the most expensive, and, in theory, the most capable. The question that has gnawed at me is the obvious one: for the work I actually do, which level is worth it?

  1. A sixth setting, ultracode, is not really another point on this scale. It is an opt-in trigger for multi-agent orchestration through Claude Code’s Workflow tool. Rather than making one agent think harder, it fans a task out across many subagents that work in parallel and then synthesize. That is a different axis from the linear effort dial, and a different cost structure, so I have set it aside here. This post is about the one knob you turn most often. ↩

Continue reading →

When Refusals Don’t Translate

An Experience Report from a German-Locale On-Device LLM

20 min read

I was preparing a new release of my German verb-conjugation iOS app, Konjugieren, and I noticed something strange about its on-device AI tutor. The tutor would occasionally produce a polite German refusal, “Ich kann dir keine Filmempfehlungen machen…”, and then render that refusal inside the speech bubble as if it were a verb-conjugation lesson. The user, who had asked something perfectly reasonable, would see the refusal appear in the conversation as a totally normal-looking response. There was no error and no fallback. The model had simply declined, and the app had presented the decline as if it were content.

Continue reading →

Trust, Then Verify

A Claude Code Skill for SwiftUI Build and UI Verification

37 min read

The single highest-leverage practice in agentic iOS coding, as of mid-2026, is the one Anthropic’s Best Practices for Claude Code names directly: “Give Claude a way to verify its work.” On the iOS side, that practice has been hard to apply. I have built a Claude Code skill called ios-build-verify that makes it cheap.

Continue reading →