---
title: "The Web Was Clocked to Human Reflexes. Agents Don't Have Reflexes."
canonical: "https://current.tinyfish.ai/issue/22/echoes/article/12032/the-web-was-clocked-to-human-reflexes-agents"
publication: "TinyFish"
publisher: "TinyFish"
language: "en-US"
guide: "https://current.tinyfish.ai/llms.txt"
issue: 22
section: "echoes"
section_name: "Echoes"
published: 2026-03-25
updated: 2026-03-26
word_count: 109
source_links: 0
---

# The Web Was Clocked to Human Reflexes. Agents Don't Have Reflexes.

*March 25, 2026*

[Read on the website](<https://current.tinyfish.ai/issue/22/echoes/article/12032/the-web-was-clocked-to-human-reflexes-agents>)

HTTP/1.0 opened a fresh TCP connection for every single request. A brutal performance penalty, and nobody cared, because the client on the other end was reading, thinking, moving a cursor. The protocol's overhead hid inside human hesitation.

Every layer built on top inherited that calibration. Apache's keepalive timeout defaulted to 15 seconds: roughly the pause between clicks. Rate limits sat at single-digit requests per second. The Retry-After header imagined a patient visitor who'd wander off and come back later.

Agents don't wander. They queue. And thirty years of infrastructure shaped by human tempo now pushes back at a speed that made sense for readers, not for software completing tasks.

## More

- [Echoes — Issue 22](<https://current.tinyfish.ai/issue/22/echoes/markdown>)
- [Issue 22](<https://current.tinyfish.ai/issue/22/markdown>)
- [Publication guide](<https://current.tinyfish.ai/llms.txt>)