---
schema: 1
type: term
title: _smuggled infinities_
description: >-
  _Smuggled infinities_ — a frame from Ben Mathysse used by Alex Komoroske —
  describes the error of letting an infinity (such as an assumption of a
  _perfect_ agent) enter an argument, after which everything downstream becomes
  absurd; real agent capability is asymptotic, so the remaining error cases
  dominate the analysis.
canonical: >-
  https://liquidgold.cc/channel/everyinc/explore/term/smuggled-infinities-c45f7798ad2c
markdown: >-
  https://liquidgold.cc/channel/everyinc/explore/term/smuggled-infinities-c45f7798ad2c.md
llms: null
parent: 'https://liquidgold.cc/channel/everyinc/llms.txt'
channel: everyinc
updated: '2026-10-23T22:12:35.346Z'
language: null
children: []
---


# \_smuggled infinities\_

Canonical: https://liquidgold.cc/channel/everyinc/explore/term/smuggled-infinities-c45f7798ad2c

Parent: [Channel index](https://liquidgold.cc/channel/everyinc/llms.txt)

## Definition

_Smuggled infinities_ — a frame from Ben Mathysse used by Alex Komoroske — describes the error of letting an infinity (such as an assumption of a _perfect_ agent) enter an argument, after which everything downstream becomes absurd; real agent capability is asymptotic, so the remaining error cases dominate the analysis.

**_Smuggled infinities_** is a frame Alex Komoroske attributes to his friend **Ben Mathysse**: the moment an infinity — something like *perfect* — enters an argument, everything downstream of it becomes absurd. The trap is easy to fall into when reasoning about AI agents: imagine the agent is perfect and it will never make a decision you dislike. But real capability is **asymptotic**, not infinite. At 99.99% reliability, the one $5,000 mistake is game over. [^bb2c42aa@4009]Many agent value propositions look like a **logarithmic value curve crossing an exponential cost curve**: amazing at first, underwater soon after. Arguments built on an assumed perfect agent hide the cost side of that curve — so evaluating agentic systems means asking where the infinity was smuggled in, and what the picture looks like at realistic, less-than-perfect reliability. [^bb2c42aa@4009]Komoroske coins a companion term, **_smuggled intelligence_**: when evaluating how smart an LLM is, beware smuggling **your own intelligence** into the test — who prompted it, what they gave it, how it was set up. The most important input to an LLM's output is the *user*; prompting skill is a real, distinct intuition with little to do with technical savviness. And unless you actively seek **disconfirming evidence**, the model will happily hand you confirming evidence for anything. [^bb2c42aa@4086]- **Smuggled infinities**: once an infinity like *perfect* enters an argument, everything downstream is absurd. [^bb2c42aa@4009]- Agent capability is asymptotic — at 99.99%, the one costly mistake is game over. [^bb2c42aa@4009]- **Smuggled intelligence** is the mirror trap: your own setup and prompting hidden inside an LLM evaluation. [^bb2c42aa@4086]- Seek disconfirming evidence; the model will not volunteer it.