{
  "slug": "why-your-gpt-5-outputs-are-shallow-or-bloated-and-how-to-fix-it",
  "title": "Why Your GPT-5 Outputs Are Shallow or Bloated (and how to fix it)",
  "date": "2025-10-01",
  "featuredClaim": "GPT-5's router defaults to shallow, cost-optimized settings—explicit phrases force deeper reasoning and controlled output length.",
  "description": "GPT-5 uses a router that independently controls reasoning depth and output length, defaulting to cost-optimized settings that produce shallow or bloated results. The article explains how explicit phrases like 'Think hard about this' force deeper reasoning, while specifying exact word counts or paragraph ranges controls verbosity. Together, these two instruction types override the router defaults for better outputs.",
  "keyPoints": [
    "GPT-5 follows precise instructions better than prior models but performs worse with vague prompts, built for AI agents that must execute exactly",
    "A router makes two independent decisions per request: reasoning depth (low/medium/high) and verbosity (low/medium/high), defaulting to cost-optimized settings",
    "Explicit phrases like 'Think hard about this' force high reasoning, while vague emphasis like 'This is critical' fails",
    "Setting exact output boundaries (e.g., '100 words or less' or '600 to 800 words') controls verbosity for different audiences"
  ],
  "topics": [
    {
      "id": "tools",
      "slug": "ai-tools",
      "label": "AI Tools",
      "description": "Practical tools and platforms for AI implementation"
    },
    {
      "id": "implementation",
      "slug": "ai-implementation",
      "label": "Implementation",
      "description": "Hands-on implementation techniques and frameworks"
    }
  ],
  "claims": [
    "GPT-5 follows precise instructions better than previous models but performs worse when prompts are vague.",
    "GPT-5 routes every request through a router that independently selects reasoning depth and output verbosity.",
    "The router defaults to low reasoning and medium verbosity because those settings are cheapest to run.",
    "Explicit phrases like 'Think hard about this' force high reasoning, while vague emphasis like 'This is critical' fails.",
    "Setting exact word counts, such as 100 words or 600 to 800 words, controls verbosity."
  ],
  "claimTitles": [
    "Precision Prompting Shift",
    "Router Controls Two Dials",
    "Cost-Optimized Defaults",
    "Reasoning Trigger Phrases",
    "Explicit Output Boundaries"
  ],
  "originalUrl": "https://aiadopters.club/p/gpt-5-reasoning-depth-output-scope",
  "claimProvenance": [
    "source-summary",
    "source-summary",
    "source-summary",
    "author-interpretation",
    "author-interpretation"
  ],
  "quote": "GPT-5 flipped this. It follows precise instructions better than any previous model but performs worse when you're vague.",
  "keyStatistics": [
    {
      "stat": "100 words or less",
      "context": "Recommended compressed output length for executive updates that senior people scan in under 30 seconds"
    },
    {
      "stat": "3 to 5 paragraphs",
      "context": "Recommended standard briefing length for team coordination where colleagues need causation context"
    },
    {
      "stat": "600 to 800 words",
      "context": "Recommended comprehensive documentation length for reference materials used by multiple teams over weeks"
    }
  ],
  "supportingContext": "The article presents a practitioner framework based on Kamil Banc's analysis of GPT-5's architectural changes, specifically its router system that makes independent decisions about reasoning depth and verbosity. The methodology relies on testing specific instruction phrases against the router's cost-optimized defaults, distinguishing between explicit cognitive commands that work and vague emphasis phrases that fail. Practitioners can apply this by adding reasoning triggers like 'Think hard about this' for high-stakes decisions such as financial planning or risk evaluation, while specifying exact word counts matched to audience needs. The author acknowledges a trade-off: forcing higher reasoning increases processing time and token cost, so it should be reserved for situations where getting it wrong once costs more than the compute. The framework is framed as practitioner experience rather than peer-reviewed research, so readers should verify results against their own use cases.",
  "canonicalUrl": "https://kbanc.com/claims-library/why-your-gpt-5-outputs-are-shallow-or-bloated-and-how-to-fix-it",
  "markdownUrl": "https://kbanc.com/md/claims-library/why-your-gpt-5-outputs-are-shallow-or-bloated-and-how-to-fix-it.md",
  "jsonUrl": "https://kbanc.com/api/claims/why-your-gpt-5-outputs-are-shallow-or-bloated-and-how-to-fix-it.json",
  "source": {
    "publisher": "AI Adopters Club",
    "title": "Why Your GPT-5 Outputs Are Shallow or Bloated (and how to fix it)",
    "url": "https://aiadopters.club/p/gpt-5-reasoning-depth-output-scope"
  }
}