In 30 seconds
Theo Browne says he has worked in terminals since he was 13, but finds their familiar panel and shortcut arrangements increasingly burdensome when several tasks run at once.
- 1A longtime terminal userTheo has spent much of his working time in terminals since age 13.
- 2Changing tradeoffsHe says terminals historically involved some upfront cost but less mental overhead, a balance he thinks has shifted.
- 3Too many concurrent tasksRemembering shortcuts and assigning panels to tasks becomes harder as the number of tasks grows.
Takeaways
- A familiar terminal workflow can still become difficult to manage as concurrent tasks multiply.
- Remembering which shortcut and panel belongs to each task adds mental overhead.
- A fixed panel arrangement can break down when another task arrives.
Read the edited text by chapter
When panel arrangements stop scaling
Theo explains why he is questioning a familiar terminal workflow. He describes the cognitive effort of tracking multiple tasks and panels.
Since I was 13, I have spent much of my time running, working, auditing and doing my daily tasks in a terminal. But I do not think terminals are always the right shape for what we do today, and I think it is time to acknowledge that.
Historically, terminals were an option with a little more upfront cost and less mental overhead. When you are working on three or more things at once, though, keeping track of which task is where becomes annoying. You have to remember which shortcut takes you to which thing.
You start building a mental system: these three panels belong to three tasks, a fourth panel to another, and a fifth is a flexible space for whatever comes up. Then a sixth task arrives, and the whole model breaks down.
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.