Make It Better Reel FINAL

Video thumbnail: Make It Better Reel   FINAL
Oct 30, 20261m 14s video lengthNate Herk | AI Automation

The Signal

Forcing an AI to innovate 100 times in a row on a static website reveals a core tradeoff between model output and prompt intent. When constrained to ship a bold change at every step without a governing vision, models prioritize additive clutter over coherent improvement, highlighting how iterative prompting can backfire if not carefully bounded.

The Case

The Experiment

  • An experimenter tested Claude Code — an AI-powered coding assistant — by issuing 100 consecutive prompts to improve a "horrible coffee shop website."0:00
  • The instructions specifically demanded that the model "look at the site first," make a "bold change" that improves conversions or design, and "ship a change every time" while avoiding small tweaks.

Model Divergence

  • Opus 5.5 — the most capable model version in the set — proved far more expansive and runaway in its output than Sonnet 5.5, which operated with greater constraint.
  • Opus ran for 8.5 hours and generated 21,000 lines of code, while Sonnet completed its task in under 2 hours and produced fewer than 3,000 lines.

Outcomes and Interpretations

  • Rather than meaningful optimization, the repetitive prompting led to feature bloat, including decorative leaves, extra text, and a non-functional Spanish translation toggle.0:31
  • The experimenter observed that the models ignored the internet entirely, which surprised them, and concluded that "innovate without a vision turns into adding."1:00
  • The process eventually broke the coffee shop site, suggesting that aggressive, unguided iteration effectively acts as a degradation mechanism.

The 1 Minute Signal Take

This experiment illustrates that model-generated improvements are highly sensitive to constraints; when you force volume over strategy, you get bloat. If you do not provide a clear, high-level vision, even sophisticated models like Opus will treat "innovation" as a mandate for accumulation rather than refinement.

Pro Analysis

Why It Matters

This experiment exposes a fundamental friction in AI-driven development: when agents are given autonomy to 'innovate' without a defined objective, they often equate complexity with improvement. This is a cautionary tale for any workflow relying on autonomous agents for site or software iteration.

Strategic Implications

Businesses leveraging AI for continuous integration or product development must shift from 'output-focused' prompting to 'vision-focused' prompting. The goal should be to provide the model with a clear north star, rather than treating the AI as an infinitely iterative pair-programmer that must always 'ship' something new.

Evidence & Hype Audit

The content is a specific, single-run experiment report. It is high-signal regarding the divergence between models (Opus vs. Sonnet) but should be treated as anecdotal. It lacks standardized metrics for 'improvement' or 'broken' states, reflecting a qualitative observation rather than a rigorous performance benchmark.

Counterarguments

A contrarian view might argue that the experiment was designed to fail. By demanding a 'bold change' 100 times in a row, the user effectively coerced the model into behaving like a destructive child. A different prompting strategy—one including 'refactor' or 'remove unused code'—could have yielded entirely different results.

Role-Specific Takeaways

  • Product Managers: Do not delegate feature expansion to AI without rigorous scope constraints.
  • Developers: Use these results to justify human-in-the-loop review for automated code commits.
  • Prompt Engineers: Test how different models handle 'negative' instructions to prevent feature accretion.

What to Do Next

  • Define a 'refining' prompt that explicitly forbids adding new UI elements.
  • Audit current autonomous agent pipelines for runaway code growth.
  • Implement a 'test-first' requirement for AI code changes to prevent breakage.
  • Run a comparative trial limiting the number of total lines changed per iteration.

Share this

Tags

Written by: 1 Minute Signal Editorial Team