What David Crawshaw thinks about coding agents

@david-crawshaw · 19 positions · On ppll ↗

Software engineer; co-founder and former CTO of Tailscale, previously on the Go team at Google.

David Crawshaw did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter coding agents · Newest first

Topic

All 19 design 7 AI agents 4 LLMs 3 code generation 2 coding agents 2 developer tools 2 the cloud 2 AI alignment 1 compilers 1

8 more topics

energy 1 open source 1 product management 1 scaling laws 1 semiconductors 1 simplicity 1 software quality 1 SQLite 1

Sort

Newest Oldest

Only David Crawshaw on coding agents. See everyone on coding agents

2 dated positions, 2026, in their own words. Our reading of what David Crawshaw has said — not written or endorsed by them.

2 positions so far — this page is not yet offered to search engines.

7 May 2026

Our readingCode review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal.

code generation

Their wordsthe reviewer is the principal, the contributor is the agent, and code review only worked because the reviewer could cheaply infer effort from reading the code. Agents collapse that signal.

↗The agent principal-agent problemcrawshaw.io 1st of 3 in this piece
7 May 2026

Our readingA person directing an AI agent rather than writing code themselves has no incentive to actually read the resulting code or engage seriously with reviewer feedback.

Their wordsThere is no incentive for the human driving the agent to actually read the code or spend time thinking about what the reviewer says.

↗The agent principal-agent problemcrawshaw.io 2nd of 3 in this piece