Software Development with Code Generators

What is AI Even Good At?

Command Line Ninja Moves

HTML & CSS

Checking Web Pages for Anything

Filler

Boilerplate

Chores

1. Renaming a hundred files
2. Scanning a hundred files to look for a single line
3. Reordering a hundred citations.
4. Taking a document or outline and making a halfway decent presentation out of it.
5. Rewriting a hundred bullet points to make it look not plagiarized.

Pleasant Surprises

Applying Market Standard Industry Conventions

Suggestions

Example Specification Suggestions

---
  PM Review: Gaps & Suggested Additions

  1. Platform Coverage is Incomplete

  The blueprint focuses heavily on Twitter/X but misses:
  - LinkedIn - Huge for B2B; uses OG tags but displays images differently (crops to different ratios)
  - WhatsApp/iMessage - Dominant for "share" buttons on mobile; WhatsApp caches aggressively and is hard to debug
  - Slack/Discord - Professional contexts; have their own preview quirks

  Suggested addition: A "Platform-Specific Considerations" section.

  2. No Character Limits Mentioned

  Platforms truncate differently:
  - og:title: ~60-70 chars before truncation
  - og:description: ~160-200 chars
  - Twitter title: 70 chars

  Suggested addition: Add truncation guidance or a helper that enforces limits.

  3. Missing Debugging/Validation URLs

  The doc says "use social validators" but doesn't list them:
  - Facebook: https://developers.facebook.com/tools/debug/
  - LinkedIn: https://www.linkedin.com/post-inspector/
  - Twitter: https://cards-dev.twitter.com/validator

  Suggested addition: Concrete validator URLs in the Validation section.

  4. Image Fallback Chain Not Defined

  What's the cascade when shareImage is missing?
  - Page-specific image → Collection default → Site default?
  - Should certain content types (articles vs. profiles) have different defaults?

  5. Article-Specific Properties Missing

  For blog/news content, these matter:
  - article:published_time
  - article:modified_time
  - article:author
  - article:section

  6. No Mention of JSON-LD/Structured Data

  OG tags and Schema.org/JSON-LD serve different purposes but are complementary. Worth noting the relationship.

  7. og:locale for Multi-Language

  The doc mentions i18n but doesn't show og:locale or og:locale:alternate tags.

Design System Conventions

Diagrams as Code

Scanning Large Codebases

Interpreting Error Messages

Giving Beginners Courage

Rapid Documentation

Robust Git Commits

Robust Code Comments

UI & Design Variants

Responsive Front-End

Appropriate Animations

Foreign Frameworks and Libraries (that are in Wide Use)

Picking Up where You Left Off

Being Cooperative

Boosting Confidence

Iteration Stamina

Rupture and Repair

Markdown & JSON & CSV

Scanning and Reading Documentation

What is AI Bad At?

Completing a complex task you gave it

Being honest

Limitations of AI Code Assistants and Code Generator AI

Key Limitations of AI Code Assistants

A diagram depicting key limitation categories: Context, Creativity, Complexity, Security, Collaboration, and Compliance.

• Poor Contextual Awareness: AI models excel at pattern recognition and syntax, but miss deeper project or business rules—leading to code that "looks right" but misses the real requirements. ^{[ucph8r] [9f363s] [17262x] [8hy165]}
• Training Data Issues: Their knowledge comes from public codebases, so they may suggest outdated methods, insecure practices, or infringe on licenses unless carefully audited. ^{[ucph8r] [9f363s] [vk4uhi]}
• Limited Creativity and Design Thinking: AI can't innovate or strategize; for open-ended tasks or complex algorithm design, its suggestions lack originality and critical insight. ^{[ucph8r] [9f363s] [8hy165]}
• Handling Edge Cases: Rare scenarios, multi-step error handling, and intricate algorithms often stump AI, resulting in incorrect or suboptimal code that requires manual correction. ^[9f363s]
• Collaboration Breakdown: AI-generated code discourages peer learning and team discussion, sometimes causing confusion about intent or logic. ^[ucph8r]
• Increased Dependency Risks: Overreliance can erode skills and discourage developers from deeply engaging with the codebase. ^[ucph8r]
• Security and Compliance: AI-generated code has been shown to leak secrets, bypass reviews, and increase critical vulnerabilities, with additional risks when handling sensitive data and compliance mandates. ^[vk4uhi]

Why Some Engineers Are Giving Up on Vibe Coding

A split image: professional engineers reviewing an AI-generated pull request filled with questionable code, side-by-side with increased security flags and reviewer comments.

• Review Overload: Apiiro's 2024 research found pull requests with AI code required 60% more review comments—especially on security issues—creating review fatigue and slowing delivery. ^[vk4uhi]
• Higher Vulnerability Rates: Projects using AI assistants saw a 2.5x increase in critical vulnerabilities, faster code merges (often bypassing human checks), and a 40% jump in secrets exposure. ^[vk4uhi]
• Productivity Paradox: Contrary to claims, recent studies show experienced developers took about 19% longer to finish issues when using AI tools—the time lost to fixing, checking, or refactoring AI-generated code often outweighs purported efficiency gains. ^[7rrgpy]
• Decreased Trust and Frustration: Engineers reported frustration with superficial tests, hallucinated logic (code that "compiles but collapses in production"), and AI failing to respect proprietary conventions or nuanced requirements. ^{[17262x] [8hy165] [7rrgpy]}

Ongoing Responses and Mitigation Strategies

A flowchart showing improved human-in-the-loop code workflows, robust context feeding, integrated security scan, and manual code review checkpoints.

• Enhanced Context Feeding: Teams are developing practices to give AI assistants more explicit instruction and business context, so outputs fit real requirements rather than generic templates. ^{[17262x] [8hy165]}
• Human-in-the-Loop Review: Critical code is subjected to deeper manual review, particularly for security, compliance, and architecture decisions. ^{[17262x] [vk4uhi]}
• Tool Improvements: Vendors are building better feedback loops, transparency features (allowing the AI to indicate confidence or request confirmation), and improved static analysis integration to catch hallucinations and vulnerabilities earlier. ^[17262x]
• Security-First Defaults: Organizations are closing AI integration gaps by masking secrets, enforcing compliance, and running security scanners on all AI-generated code before deployment. ^[vk4uhi]
• Workforce Development: There is renewed emphasis on retaining manual coding skills and fostering collaborative environments where AI is a support—never a replacement—for real engineering insight. ^{[ucph8r] [8hy165]}

Citations