Skip to content
AI ConnectPowered by VELENTIS
AI-generated2 min

Resisting Code Pollution: Developers Launch the 'No AI Slop Manifesto'

At the AI Engineer Code Summit, engineers published the 'No AI Slop Manifesto', demanding deep human understanding instead of unvetted, high-volume automated code generation.

This article was AI-generated and published automatically. Context, labelling and all sources at the end of the article.

(KI-generiertes Symbolbild: Gemini / AI Connect)

During the AI Engineer Code Summit 2026, leading software developers and speakers drew a firm line against the uncritical deployment of generative models. On November 12 and 13, 2026, Dex Horthy, Philip Kiely, and Kent C. Dodds, alongside other summit participants, published the 'No AI Slop Manifesto'. The document was launched simultaneously via a GitHub Gist and the website slopmanifesto.com, instantly sparking widespread discussion across the technical community. It addresses the accelerating influx of substandard, unexamined machine output across enterprise codebases and internal documentation.

The manifesto deliberately frames itself as a contemporary parallel to the landmark Agile Manifesto of 2001. Just as the agile pioneers pushed back against rigid waterfall methodologies, this new initiative challenges the blind trust placed in raw generative throughput. The authors use the term 'AI slop' to describe automated code snippets, pull requests, and technical memos pushed into workflows without rigorous human validation. Engineering leaders are discovering that inflating generation speed often fails to deliver meaningful improvements in end-product quality.

The authors anchored their framework around three core operating tenets designed to guide engineering teams and leadership. Foremost among them is 'outcomes over output', emphasizing durable business and functional value rather than raw token generation. The second pillar, 'understanding over speed', demands that programmers maintain a complete conceptual grasp of their codebase rather than chasing rapid code synthesis. Finally, 'our own thinking over a model’s first draft' asserts that human critical reasoning must remain the definitive anchor of the software development lifecycle.

This shift in perspective carries concrete operational consequences for the broader software industry. When large language models and autonomous agents can generate arbitrary volumes of code and documentation at negligible marginal cost, project overhead inevitably shifts downstream. The primary bottleneck is no longer the synthesis of new lines of code, but the rigorous verification, auditing, and maintenance of incoming automated drafts. Reviewers face mounting fatigue from low-effort pull requests that require disproportionate human labor to review and debug.

The debate reflects a broader reckoning across professional software engineering, where the structural limitations of raw automation are becoming evident. While automated code completion tools were initially hailed as an unalloyed productivity multiplier, complex production environments are now revealing severe maintenance overhead and compounding technical debt. Unvetted model outputs frequently introduce subtle bugs that pass initial unit tests while degrading architectural integrity over time. The signatories caution that development teams risk relinquishing intellectual ownership of their systems if output generation remains unchecked.

Consequently, rigorous quality assurance is reclaiming its role at the core of technical leadership and engineering culture. The manifesto urges organizations to establish demanding verification criteria and prevent developers from delegating ultimate code accountability to probabilistic engines. Engineers are increasingly expected to act as critical auditors and system architects whose core value lies in deep structural discernment and failure analysis. The No AI Slop Manifesto ultimately signals an important maturation phase for an industry moving past speculative enthusiasm toward disciplined engineering reality.

What this means for you

For technology leaders and software engineers, the initiative signals a fundamental paradigm shift in how generative AI is utilized. Pure speed advantages during initial drafting rapidly lose their value when they multiply the labor required for reviews and debugging. Organizations utilizing AI tooling must actively invest in rigorous verification protocols and strengthen internal code comprehension.

Perspectives

Coverage: 1× US · 2× Other

One story, several angles: how each source frames the topic, each with a verbatim quote.

  • gist.github.comUS

    The original manifesto presents itself as a value-based charter modeled after the Agile Manifesto, emphasizing human responsibility and thoroughness over an unreviewed flood of AI outputs.

    Original quote

    „Slop happens when we pass AI output along without taking responsibility for the quality or the reader's experience.“

    gist.github.com
  • daily.devOther

    Daily.dev summarizes the core tenets of the manifesto while highlighting the community's split reaction between code review scalability and skepticism regarding corporate incentives.

    Original quote

    „Discussion is split between practical debate on how to review AI-generated PRs at scale and broader skepticism“

    daily.dev
  • explainx.aiOther

    Explainx.ai frames the manifesto as an actionable charter for engineering teams that must push back against pure token throughput metrics in favor of an updated review culture.

    Original quote

    „It is a team charter for the moment agent swarms can produce more text and code in a day“

    explainx.ai

Source classification is maintained editorially (political spectrum only where consensus is broad; vendor communication is PR, not journalism). Unlabelled sources are unclassified: we do not guess.

Evidence

Solidly sourced
62/100
  • The named initiators of the manifesto include Dex Horthy, Philip Kiely, and Kent C. Dodds.

    single source
  • The manifesto establishes core tenets including 'Outcomes over output', 'Understanding over speed', and prioritizing human thinking over a model's first draft.

    single source
  • Drawing inspiration from the 2001 Agile Manifesto, the document highlights that project bottlenecks and costs shift from content generation to verification and quality assurance.

    single source

The evidence score is computed, not hand-set: from confidence, the number of sources and the share of verified statements.

Source & transparency

As of: November 15, 2026

AI-generatedAI-generated: produced automatically from vetted sources with technical quality checks (source, quote and figure verification); no human sign-off of each item before publication

Sources
3
Verified statements
0 / 3
Evidence score
62Solidly sourced

Want to put this into practice?

We connect you with suitable AI providers from the DACH region, free of charge and without obligation.

What's next?