Grey Golus logoGREYGOLUSStart here

01 // Resource guide

Updated June 2026

AI models

Understand what a model is, what changes between model tiers, and how to choose enough capability for the job without wasting time or money.

Bottom line

Match the model to the job, not the hype. Start with the default, then change only when speed, cost, privacy, or quality gives you a reason.

01 // City map

The model is the building

A company owns a plot in the AI city. It builds a family of models on that plot. The app or harness you use is the storefront where you enter and work.

Company

01
Plot

The organization building and operating the model family.

Model

02
Building

The underlying intelligence that interprets inputs and generates outputs.

Harness

03
Storefront

The chat, agent, coding tool, or app that gives you access to a model.

02 // Model jobs

Most choices fall into four lanes

Capability-first

01
Deep work

Use for difficult reasoning, ambiguous planning, complex synthesis, or work where a weak answer creates real cost.

Balanced default

02
Start here

The best starting point for normal writing, analysis, file work, and everyday agent tasks.

Fast and efficient

03
Speed

Use for simple transformations, classification, extraction, and high-volume repeat work.

Specialized or local

04
Control

Use when the job needs a specific medium, tool, privacy boundary, or self-hosted model.

03 // Five dials

Compare trade-offs that survive model-name changes

DialQuestion to askWhen it matters
CapabilityCan it reliably handle this level of reasoning and ambiguity?Complex or high-consequence work
SpeedHow quickly does it respond or finish an agent task?Interactive and repeated work
Cost / usageIs the quality gain worth the extra usage?Large files, long sessions, automation
ContextCan it use all the files and instructions needed at once?Research, codebases, long histories
Privacy / controlWhere is data processed and what can the system retain or access?Personal, school, or restricted information

04 // Quick choice

A three-step model decision

  1. 01

    Start with the recommended default

    The provider usually chooses a balanced model for normal use. Do not optimize before you have a problem.

  2. 02

    Run one representative task

    Use a real example, a clear definition of done, and the same prompt when comparing alternatives.

  3. 03

    Change one dial

    Move up for quality, down for speed or usage, or local for control. Keep the rest of the workflow unchanged.

  • Do not use the largest model for every small task.
  • Do not treat benchmark rank as proof that a model fits your workflow.
  • Do not confuse the model with the app, plan, connector, or agent using it.

Official sources