Treat Agent Output Like Compiler Output | Skip
Why our discomfort with AI-generated code reveals exactly what we haven't built yet, and what the compiler analogy teaches us about trusting coding agents.
Philip Su's recent post argues that code reviews are not just impractical in the age of coding agents, they're headed toward being irresponsible . He's right on trend. But I think the framing of "lights-out codebases" skips over the more interesting and uncomfortable question: why does lights-out feel so scary , and what does that fear actually tell us? The answer, I think, is hiding in something we already used once before and then promptly forgot we did: the compiler. Nobody Reviews Compiler Output Think about how you relate to your compiler. You write C++, Rust, Go, and the toolchain spit
saved by
related reading
- If you are good at code review, you will be good at using AI agentsseangoedecke.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Your job is to deliver code you have proven to worksimonwillison.net
- I built an AI code review agent in a few hours, here's what I learnedsourcebot.dev
- Would you fly on an AI-coded plane | Hackle's bloghacklewayne.com
- The Eternal Sloptember | the singularity is nearergeohot.github.io
- Why We Built Our Own Background Agentbuilders.ramp.com
- Code was our medium for thoughtwattenberger.com
- Auto-review of agent actions without synchronous human oversightalignment.openai.com
- Now – Updates from the Linear teamlinear.app
- Thoughts on slowing the fuck downmariozechner.at
- A Practical Approach to Verifying Code at Scalealignment.openai.com