Skip to content
daily-hour-news·

🛠️Willison: Lines of Code Do Measure Agent Productivity

TL;DR

Simon Willison argues lines of code is a fair productivity signal with coding agents, because the pre-agent ceiling was real. A strong human day was 200 debugged lines and 50 to 60 was typical.

Simon Willison argues lines of code is a fair productivity signal with coding agents, because the pre-agent ceiling was real. A strong human day was 200 debugged lines and 50 to 60 was typical. Agents push that toward a thousand, but the new limit is cognitive capacity to review it.

Key Points

1

Pre-agent baseline: 200 lines of debugged production code is an excellent day, 50-60 is typical

2

Agents can reach roughly 1,000 lines a day at equivalent quality, but only with senior-level skill

3

Teams still need multiple engineers to load-balance review capacity, not typing throughput

4

Warns coding agents erode conceptual integrity, the Mythical Man-Month idea of software without surprises

5

From an August 2026 Talking Postgres episode with Claire Giordano

Why It Matters

The bottleneck moved from writing code to holding it in your head, which argues for smaller diffs and tighter scope rather than longer agent runs.

Quick Facts

Simon Willisoncoding agentsdeveloper productivityconceptual integritycode reviewAI engineering

Frequently Asked Questions

Why does this matter?

The bottleneck moved from writing code to holding it in your head, which argues for smaller diffs and tighter scope rather than longer agent runs.

What happened?

Simon Willison argues lines of code is a fair productivity signal with coding agents, because the pre-agent ceiling was real. A strong human day was 200 debugged lines and 50 to 60 was typical.

Comments

Subscribe to join the conversation...

Be the first to comment

Enjoyed this article?

Get it daily. 7am. Free. Reads in 5 minutes.

Join 3,249 builders reading daily.

Also get