← Home
AI Breakdown · May 24, 2026 · 00:26:16

Why Agents Still Need Humans

NLW examines the next wave of human-agent collaboration, drawing on Dan Shipper's essay "After Automation" and experiments from Every. He argues that rather than eliminating work, AI agents are creating more expert-level human roles. The episode discusses shared team agents, the "human sandwich" interaction model, the limitations of fully autonomous agents, and why tools like Codex and Claude Code suggest a semi-synchronous future where humans manage agent work across devices.

This summary was generated from show notes and public descriptions, not from a full transcript review. Details may contain inaccuracies.

Canon

Automation shifts human work toward more complex, expert tasks rather than eliminating it.

Highlights

The Human Sandwich Model
A model of human-agent interaction where humans provide input at the start and end of an agent's work.
Shared Team Agents
AI agents designed for team use rather than individual deployment improve collaboration and oversight.
Limits of Fully Autonomous Agents
Fully autonomous agents like OpenClaw struggle with reliability, requiring human-in-the-loop oversight.
Semi-Synchronous Future
Tools like Codex and Claude Code suggest a future where human-agent work happens asynchronously but with partial synchronicity.
Was this useful?