Everyone Says Loop, Nobody Defines It
Matt Van Horn’s X article “WTF Is a Loop? Peter Steinberger vs. Boris Cherny” opens with an observation about AI-coding discourse: “The most repeated sentence in AI coding this week is six words long, and almost nobody saying it can define it.” The article contrasts how Peter Steinberger and Boris Cherny each mean different things by running agents “in a loop,” after one tweet “had the entire timeline in a chokehold.”
Even from the preview, the meta-point stands on its own: AI-coding vocabulary spreads faster than its meaning. A term coined by practitioners with a precise workflow behind it gets repeated as a slogan, and within a week the same word covers incompatible practices. When two named experts disagree on what a core term means, copying the term without copying the underlying workflow copies nothing.
Source returned limited text — captured what was available (article preview only; full comparison behind X login).
Related
- Morning Agents from the Phone - Boris’s Full Daily AI Workflow — Boris’s actual loop-like practice, the concrete referent behind one side of the definitional fight
- Give the Agent a Way to Verify Its Own Work — what makes any agent loop meaningful: without a verify step, “running in a loop” is just repetition
- Agent Loops Only Work When the Output Is Binary — essay candidate that answers the definitional fight with one criterion
- Stop Copying AI Workflows From People With Unlimited Tokens — essay candidate: the word travels without its price tag, not just without its meaning