In 30 seconds
Theo says copy-pasting is not a good use of time, but he was initially uninterested in asking an agent to divide work among five others. He argues that assigning predefined personas and roles misses what makes agents and AI dynamic.
- 1Beyond copy-pastingTheo says copy-pasting is not the best use of his time.
- 2Skepticism about delegationHe was not initially interested in asking an agent to spin up five others to divide work.
- 3Agents are dynamicTheo thinks predefined personas miss a central strength of agents and AI: their dynamic nature.
Takeaways
- Copy-pasting is not the best use of a developer's time.
- Theo was initially skeptical of having an agent split work among five agents.
- He argues that predefined personas miss the dynamic character of agents and AI.
Read the edited text by chapter
From copy-pasting to agents
Theo considers the use of agents to divide work. He describes his initial skepticism about spawning several workers.
Copy-pasting is not the best use of our time. But I wasn't that interested in telling my agent to spin up five agents to split up work, especially when I saw people creating different personas and roles for all those workers.
The problem with fixed personas
Theo questions assigning preset personas and roles. In his view, this misses the dynamic nature of AI agents.
That made no sense to me, and I would argue it still doesn't. Predefining personas fundamentally misses what is cool about agents and AI as a whole: they're dynamic.
More from this channel
38:47EN
Theo - t3․gg· Oct 28, 2026Theo’s Long-Running Agent Experiments: Verification, Compute and CostTheo Browne · Ping LabsA skateboard game and two compiler projects show how repeated checks and flexible compute can sustain agent work—and how expensive those loops can become.
36:07ENTheo - t3․gg· Oct 27, 2026Theo on Token Costs, Coding Agents, and the Price of AI CapabilityTheo Browne · Ping LabsA viral estimate of Lauren's AI spending prompts a closer look at cache pricing, benchmarks, and the changing work of coding agents.
30:37ENTheo - t3․gg· Oct 26, 2026Theo’s Three Skills for Reviewing and Shipping with Coding AgentsTheo Browne · Ping LabsHow sol-loop, full-send and full-stop encode review, verification and different levels of merge authority.
0:43ENTheo - t3․gg· Oct 23, 2026Theo Distinguishes Security Vulnerabilities from Active AttacksTheo Browne · Ping LabsA short explanation of why disclosed software flaws and reported attacks are different kinds of security news.
29:22ENTheo - t3․gg· Oct 22, 2026Theo on Security Vulnerabilities, Stolen API Keys and AITheo Browne · Ping LabsA look at the gap between vulnerability disclosure and patching, and a speculative account of why stolen inference keys may be valuable.
31:13ENTheo - t3․gg· Oct 20, 2026Theo on Why Smarter Models Help More Than DevelopersTheo Browne · Ping LabsFrom game modifications to compiler experiments, Theo revisits his assumptions about who benefits from more capable AI.