17Book intelligenceFuture2025

Vibe Coding

Source · Future
First published
2025
Edition
First edition, 2025
Format
paperback
Publisher
IT Revolution Press
ISBN-13
9781966280026

AskNex reference artwork. The publisher's cover appears only under an approved rights record.

by Gene Kim & Steve Yegge

An argument that AI assistants change what a software engineer is for, and a set of practices for using them to build production-grade systems rather than demos.

Makes the case for AI-assisted engineering from people who have run large engineering organisations.

AskNex explains and applies the ideas in this book in its own words. Nothing on this page is quoted from the book, and the page does not stand in for it: the argument, the evidence and the voice are the author's, and reading the original remains the deeper path.

In these topics
01Part

The core idea

The scarce skill is no longer typing code but specifying, steering and verifying it. Engineers who delegate well to AI multiply their throughput; the ones who refuse fall behind, and the ones who trust blindly ship debt.

02Part

The ideas

2 mental models, in the order they build on each other.

  1. 01

    Chat-oriented programming

    Describe the intent, review the result, keep the loop tight. The conversation is the work.

  2. 02

    Context is the product

    Output quality tracks the quality of the codebase, constraints and intent you give the model.

03Part

What the book argues

AskNex's own paraphrases of the positions this book takes, as they are held in the knowledge graph. Not quotations, and not the whole book.

  1. 01

    The scarce engineering skill becomes specifying, steering and verifying; engineers who delegate well multiply their throughput.

    ArguesAI-assisted software engineering
    Kim & Yegge
  2. 02

    Work in a tight loop: describe the intent, review the result, correct, repeat; never accept a change larger than you can read.

    ArguesAI-assisted software engineering
    Kim & Yegge
  3. 03

    Output quality tracks the context you supply: the codebase, the constraints and the intent.

    ArguesAI-assisted software engineering
    Kim & Yegge
  4. 04

    Vibe coding accelerates exploration; production software still needs tests, review and architecture the model cannot own.

    CautionsSoftware quality and review
    Kim & Yegge
Ideas it contributes to5 ideas
  1. 01

    AI-assisted software engineering

    Specifying, steering and verifying code produced by a model, rather than typing it.

  2. 02

    Working with AI

    Using a fast, fallible model as a collaborator whose strengths are uneven and must be mapped.

  3. 03

    Software quality and review

    Correctness, maintainability and safety of software, which a fast first draft does not supply.

  4. 04

    Career capital

    Rare and valuable skills bought with sustained effort, then spent on autonomy.

  5. 05

    Validated learning

    Treating a venture as a series of tests rather than a plan to execute.

04Part

Where it argues with other sources

Most summaries flatten this. AskNex keeps it, because the disagreement usually decides what applies to you.

Mollick qualified by Kim & Yegge

Tension 1Career capital
Agrees
Expertise is what lets you judge the output; skipping the apprenticeship to rely on the model leaves you unable to evaluate it.
Mollick, Co-Intelligence
Disagrees
Refusing these tools out of pride or fear now costs more than learning them badly would.
Kim & Yegge, Vibe Coding
Verdict
Adopt the tools now, but not in place of the apprenticeship: use them where you can already judge the output, and build the fundamentals unaided where you cannot.

Osmani qualified by Kim & Yegge

Tension 2Software quality and review
Agrees
The model gets you most of the way quickly; the last stretch of edge cases, integration and correctness is still engineering.
Osmani, Beyond Vibe Coding
Disagrees
The scarce engineering skill becomes specifying, steering and verifying; engineers who delegate well multiply their throughput.
Kim & Yegge, Vibe Coding
Verdict
The leverage is real, and so is the last stretch: delegate the draft, keep the engineering judgement, and budget time for the part the model cannot finish.
05Part

What actually matters

  • Vibe coding accelerates exploration; production still needs tests, review and architecture the model cannot own.
  • The risk of not learning these tools now exceeds the risk of using them.
06Part

Where it applies

Practical moves the book supports. Each one is a place to start, not a rule.

  1. 01Tighten the loop

    Work in small, reviewable increments; never accept a change larger than you can read.

  2. 02Feed the context

    Write the constraints, conventions and intent down once so every session starts from them.

07Part

Questions worth asking

  1. 01

    What in my workflow is still typing that should be steering?

  2. 02

    Which generated change did I merge without reading?

10Apply this to me

What are you trying to figure out right now?

AskNex will answer your situation using the ideas in Vibe Coding alongside every other source that applies — including the ones that argue against it.