lennysnewsletter.com

🎙️ How I AI: Sonnet 5 review & How to run autonomous coding agents from your phone

LLM-as-judge evals are too generous and cluster toward the middle of the scale. Claire had both GPT-5.5 and Opus 4.8 judge the outputs, and neither was spiky enough. They missed things she flagged immediately on a visual pass, like broken prototypes and ignored wireframe constraints. Models can't yet see what the human eye catches in the first screenshot.

oneusefulthing.org

What it feels like to work with Mythos

The details of the AI's decision making are not shown to me, and the process would be too long to even be worth following. The map required the AI to make judgement calls about hundreds of little choices, and it just made them, without me understanding the choices or having a chance to weigh in. In many ways, it is miraculous (I can always ask for edits at the end) on the other, it turns AI into the ultimate black box.

oneusefulthing.org

What it feels like to work with Mythos

The map required the AI to make judgement calls about hundreds of little choices, and it just made them, without me understanding the choices or having a chance to weigh in. In many ways, it is miraculous (I can always ask for edits at the end) on the other, it turns AI into the ultimate black box.

lennysnewsletter.com

🎙️ How I AI: HTML is the new Markdown: How Anthropic engineers are building with Claude Code

Engineers are becoming "compute allocators" rather than code writers. When Claude can run for eight hours on a single task, you're really deciding how to spend $500 of compute. The critical skill is no longer writing code; it's deciding what's worth building, defining the boundaries of what you need to know, and staying in sync with the agent throughout the process.