Posts Tagged ‘AIDevTools’
[VoxxedDaysTicino2026] Technical Enshittification: Why Everything in IT is Horrible Right Now and How to Fix It
Lecturer
Baruch Sadogursky is the Head of Developer Relations at TuxCare, with a distinguished career in Java and DevOps ecosystems. A Java Champion and Microsoft MVP for AI, he has authored books on these topics and is known for his candid analyses of industry trends.
Abstract
This article examines Baruch Sadogursky’s critique of technical enshittification, where software platforms degrade user experiences after gaining dominance. It explores the underlying causes, such as excessive complexity and bloat, and proposes remedies through AI, smart tooling, and refined workflows. By analyzing real-world examples and systemic issues, the discussion highlights methodologies for restoring efficiency and innovation in IT.
The Phenomenon of Enshittification in Technology
Baruch Sadogursky introduces the concept of technical enshittification as an extension of Cory Doctorow’s idea, where platforms initially attract users but subsequently exploit them at the expense of quality. In software, this manifests as bloated applications, sluggish performance, and accumulating bugs that erode reliability. He illustrates this with examples like operating systems losing files or password managers suffering repeated breaches, underscoring how such degradation is not isolated but systemic. The contexts reveal that this trend stems from economic pressures favoring monetization over maintenance, leading to innovation that often amounts to superficial changes rather than substantive improvements. The implications are profound, as they diminish developer productivity and user satisfaction, fostering a cycle of frustration in the industry.
Systemic Causes and Their Interconnections
The talk delves into how complexity has become an obstacle course in software development, with layers of tools, approvals, and abstractions slowing progress. Baruch points to attention fragmentation, where developers spend minimal time coding—around 52 minutes daily—due to distractions like meetings and context switching. He references studies showing it takes 25 minutes to refocus after interruptions, amplifying the toll of lengthy builds or code reviews. Organizational habits, such as frequent reorgs, further destroy shared knowledge, while technical debt accumulates from unrefactored legacies. Bloat exacerbates vulnerabilities, as more code lines create more attack surfaces, evidenced by rising malicious packages in repositories. The contexts connect these to broader industry dynamics, where rapid feature additions outpace quality controls. The implications include stalled innovation and heightened risks, as teams grapple with outdated contexts rather than advancing core functionalities.
AI as a Double-Edged Sword in Development
Baruch views AI as a catalyst that accelerates code generation but risks compounding technical debt through unvetted outputs. While it promises faster features, it often introduces bugs and vulnerabilities, as seen in Java’s poor performance on AI security benchmarks. He critiques the “credit card” mindset, where AI enables unchecked experimentation, leading to more complexity. However, he advocates for its responsible use in context engineering—compressing knowledge for relevance and expanding it thoughtfully. Spec-driven development emerges as a safeguard, where high-level specs guide agents, ensuring traceability. The contexts highlight the need for integrity chains to verify AI-generated code against intentions. The implications suggest AI can revitalize workflows if paired with human oversight, but without it, it perpetuates enshittification.
Organizational Reforms and Workflow Optimizations
To combat these issues, Baruch recommends streamlining processes to minimize distractions and preserve context. Agile principles, when applied purely, encourage reactive planning over rigid foresight, allowing small bets to test assumptions iteratively. DevOps practices, like automation and “you build it, you run it,” offload context to systems, reducing manual toil. Management should focus on documentation of decisions and protecting focus time. The contexts draw from attention research, showing how interruptions fragment productivity. The implications include enhanced efficiency, where teams reclaim coding time and foster cultures of continuous improvement.
Reclaiming Joy and Progress in Software Engineering
In conclusion, Baruch urges embracing these reforms to restore the joy of building software. By prioritizing context preservation and leveraging AI judiciously, organizations can escape enshittification’s grip. The talk serves as a call to action, reminding developers they are not alone in facing these challenges and that proactive changes can lead to meaningful progress.