Theo on Why Natural Language Does Not Belong in a Terminal

A brief argument that developers’ attachment to familiar terminals can shape how they imagine new interfaces.

TBTheo BrowneIntervenant · Ping Labs
Chaîne
Theo - t3․gg
Publié
9 juil. 2026
Vidéo
0:18
Lecture
1 min
Original
anglais
Ouvrir sur YouTube
En faisant défiler, la vidéo se réduit en bas à droite et continue. Les sous-titres suivent votre langue de lecture.
Langue de lectureDisponible en 2 langues
Cet article n’est pas encore disponible en français ; il s’affiche dans l’original en anglais.
RÉSUMÉ

En 30 secondes

Theo Browne argues that developers are in a skeuomorphic phase: they treat the terminal as an ideal interface because it is familiar. Although he loves terminals, he says natural language does not belong in one.

  1. 1A skeuomorphic phaseTheo says developers are leaning on a familiar interface when thinking about new ways to work.
  2. 2A beloved interfaceHe loves his terminal but does not consider it the ultimate interface.
  3. 3Natural languageHe argues that familiarity is why developers keep placing natural language in terminals.

À retenir

  1. Theo thinks developers overestimate the terminal as an interface.
  2. He believes familiarity and affection help explain its continued appeal.
  3. He argues that natural language does not belong in a terminal.
TEXTE INTÉGRAL

Lire le texte remanié, chapitre par chapitre

Transcription seule
01

Familiarity and the terminal

Theo questions the terminal as an interface for natural language. He connects its appeal to developers’ habits and affection for it.

I think software developers are in a skeuomorphic phase. We act as though terminals are the ultimate interface, even though I do not think they are particularly good interfaces. I say that as someone who deeply loves my terminal.

Natural language has no place in a terminal, but we pretend it does because the terminal is familiar. It is what we are used to, what we love, and where we like to imagine ourselves when we think about coding.

Sur la même chaîne

5 diapositives38:47EN
Theo - t3․gg· 28 oct. 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.Agents de codeIngénierie d’agentsAI cost & performance+2
5 diapositives36:07EN
Theo - t3․gg· 27 oct. 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.AI cost & performanceAgents de codeInference+1
5 diapositives30:37EN
Theo - t3․gg· 26 oct. 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.Agent skillsAgents de codeCode review & verification+2
2 diapositives0:43EN
Theo - t3․gg· 23 oct. 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.CybersecuritySoftware engineering
6 diapositives29:22EN
Theo - t3․gg· 22 oct. 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.CybersecurityAI securitySoftware engineering+1
4 diapositives31:13EN
Theo - t3․gg· 20 oct. 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.Agents de codeDeveloper productivityHuman-AI Collaboration+1