Engineering brief

Your Model Is Fine, Your System Prompt Is Sabotaging You

This engineering brief covers Your Model Is Fine, Your System Prompt Is Sabotaging You, with practical context for AI and developer-tool decisions.

Theo - t3․gg

The Brief

Codex’s system prompt enforces absurd design rules—specific border radii, icon libraries, forbidden empty states—that silently degrade output and burn tokens. This reveals that an AI tool’s harness, not the model, increasingly determines quality and cost.

Decision relevance

Read this for workflow impact, implementation trade-offs, and the claims that need technical scrutiny before they reach team planning.

Summary

The most shocking signal is that OpenAI’s Codex system prompt contains absurdly prescriptive design rules—border radii, icon libraries, forbidden empty states—that make even powerful models like 5–6 produce generic “slop.” These rules waste tokens and were only partially removed after a YouTuber raised hell. The real bottleneck isn’t model intelligence; it’s the agent harness.

Claude Code’s workflow feature lets models define programmatic sub-agent orchestration in code, which is bounded and token-efficient. Using OpenAI’s 5–6 inside Claude Code yielded quarter the token usage of Codex’s Ultra mode and better output quality, because workflows end and don’t spiral.

The tradeoff: moving to Claude Code for orchestration means juggling separate tools and subscriptions, and model-specific formatting quirks still appear. But for teams tackling complex multi-step coding tasks, this approach reduces cost and raises consistency.

Engineering leaders should audit the system prompts and agent frameworks their teams rely on. A model’s benchmark means little if the harness steers it toward wasteful, rigid behavior. Expect a shift in the AI tooling battle from model specs to prompt engineering and workflow design.

Why It Matters

System prompts and agent orchestration now dictate output quality more than model choice—ignoring this wastes tokens and degrades team productivity.

Editorial analysis

Key claims

  • Audit your AI tool’s system prompt; a strong model under a bad harness is a hidden productivity killer.

Practical use cases

  • Use this as input for tooling evaluation, workflow planning, and technical due diligence.

Risks / caveats

  • Rants about rebranding, minor UI formatting quirks, and terminal freeze anecdotes.

Who should care

  • Engineering managers, tech leads, and CTOs evaluating AI or developer tooling decisions.

Related topics

Bottom Line

Audit your AI tool’s system prompt; a strong model under a bad harness is a hidden productivity killer.

Watch

This video is blocked due to your privacy settings. To watch this video, please accept YouTube marketing cookies.

Related breakdowns

Get TL;DW

Too Long; Didn't Watch.

A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.

Free. Weekly. No hype.

Video and thumbnails remain the property of their respective creators. tldw.news provides editorial analysis, commentary, and discovery links to original content.