{"slug": "i-asked-gpt-5", "title": "I asked GPT 5.", "summary": "A developer using OpenAI's GPT-5 (referred to as 'Sol') generated a working Three.js Matrix rain effect in a single prompt, producing about 300 lines of self-contained HTML code that ran on the first try. The developer refined the result by feeding screenshots back to the model, which adjusted specific values, highlighting a visual feedback loop as the key to effective AI coding workflows.", "body_md": "# I asked GPT 5.\n\n**The prompt that did the heavy lifting**\n\nThe first version I tried was vague (\"make the matrix rain in threejs\") and it returned a flat 2D canvas effect with no depth. The second pass worked because I forced the scene into a real 3D layout. I asked for: falling glyph columns placed on a grid, each with random speed and opacity, a perspective camera drifting along the Z-axis, and a full-screen shader for that blurry CRT look. The prompt looked like this:\n\n```\nBuild a Three.js scene simulating the Matrix opening.\n- Create 80 columns of vertical falling characters (katakana + digits).\n- Each column is a separate plane with a canvas texture.\n- Randomize speed, offset and char set per column.\n- Camera starts far away and slowly moves forward (Z axis).\n- Add a post-processing bloom or glow effect (UnrealBloomPass).\n- Pure black background, green #00ff41 text.\n- Keep it in one HTML file with CDN imports.\n```\n\nThat one prompt produced working code on the first try. Not \"kinda works\" — it ran, it rained, it looked right. The camera move wasn't perfect (it accelerated like a broken elevator), but the structure was there. I had to tweak the camera easing manually.\n\n**Step-by-step workflow, if you want to reproduce it**\n\n1. Set the CDN imports for Three.js and OrbitControls + EffectComposer. Sol picked r128 from a CDN by default — pin a modern version or it'll complain.\n\n2. Generate canvas textures for each column using `fillText`\n\ninside a loop. That's what makes the glyphs look like actual code, not random squares.\n\n3. Place columns in a `GridHelper`\n\n-like pattern manually: `(i % 10) * 4 - 20`\n\nfor X, random Z spread. Depth comes from the grid, not from texture tricks.\n\n4. Move the camera along Z using a normalized time accumulator, and apply a ease-out curve. I replaced Sol's linear movement with `1 - Math.pow(1 - t, 3)`\n\n.\n\n5. Add `UnrealBloomPass`\n\nfor the glow. If you skip this, it looks like a terminal screensaver from the 90s.\n\nThe final HTML was about 300 lines, all self-contained. I opened it in a browser and it was honestly cinematic. The way the far columns blur into the dark while the near ones rush past — that only works because the camera is actually moving through 3D space, not scrolling a 2D canvas.\n\n**The real lesson about AI workflow**\n\nThis is a great use case for prompt engineering because the requirements are visual and measurable. You can screenshot the output, show it to the LLM, and ask for changes. I took the rendered frame, pasted it back into the chat, and said \"the text is too small, make the columns wider and the camera closer\" — Sol adjusted the values in the exact spots. That feedback loop is the actual magic, not the first generation.\n\nIf you're looking for a beginner-friendly way to test an AI coding agent, this is it. It's a complete guide in one file: procedural textures, scene setup, animation loop, post-processing. No backend, no build tool, no deployment needed. Just open the HTML and it runs. And if you're into LLM agents, watch how well it responds to visual critique — that's where the real workflow gains are.\n\nThe code isn't perfect. It still drops frames on a big monitor and the glyphs occasionally flash white. But for a zero-shot prompt? I've paid for worse tutorials.\n\n[OpenAI Slashes GPT-5.6 Luna Price 80%: A Pricing Deep Dive 3d ago](/en/news/4489/)\n\n[GPT-5.6 Revenue Surge: How July Beat Q2 4d ago](/en/news/4448/)\n\n[Next Pretending AI didn't write my code made me a better dev →](/en/news/4890/)\n\n## All Replies （4）\n\n[@Max75](/en/users/Max75/)Yeah, adding a slight tilt makes a huge difference. Ever tried a top-down view?", "url": "https://wpnews.pro/news/i-asked-gpt-5", "canonical_source": "https://promptcube3.com/en/news/4892/", "published_at": "2026-08-04 03:53:03+00:00", "updated_at": "2026-08-04 04:24:14.300717+00:00", "lang": "en", "topics": ["generative-ai", "ai-tools", "developer-tools"], "entities": ["OpenAI", "GPT-5", "Three.js"], "alternates": {"html": "https://wpnews.pro/news/i-asked-gpt-5", "markdown": "https://wpnews.pro/news/i-asked-gpt-5.md", "text": "https://wpnews.pro/news/i-asked-gpt-5.txt", "jsonld": "https://wpnews.pro/news/i-asked-gpt-5.jsonld"}}