15-year terminal power users: agents ended direct machine operation, systems knowledge is the moat
omarsar0 · x · 2026-10-04
YuchenjUW reflects on 15+ years as a terminal power user — Vim, shortcuts, the Matrix hacker aesthetic — and concludes terminals assumed humans operate computers directly via files, commands, and processes. Agents changed that: you state intent, and the agent drives the machine with the same languages and Linux commands we spent years learning. He argues understanding what sits beneath the abstraction still makes you a better systems thinker — a moat in the AI era.
Elvis Omazing agrees: he's fully moved away from the terminal since agents offer better interfaces, but his terminal years directly inform his sandbox and abstraction design.
More from coding & agent
- Local LLM benchmarks are mostly noise: c=1 tokens/s hides real concurrency performance — TheZachMueller · 2026-10-04
- Even Opus 5.5 ships vulnerabilities when your vibe coding requirements are vague — gefei55 · 2026-10-04
- Too many agents to track: David Khourshid loses track of what his own bots do — DavidKPiano · 2026-10-04
- Harness engineering reduced to prompts and tools, but it's what makes agents reliable — techNmak · 2026-10-04
- A model alone isn't an agent: a first-principles handbook on agent harness engineering — techNmak · 2026-10-04
- Building a Miro clone 5x on 3 local rigs: tokens/sec is useless, thinking variance hits 5x — julianharris · 2026-10-04