First check failed with 4 layout errors that all traced to one bug: the chart's bars, month labels, gridlines and milestone chips were styled with left/top/bottom offsets but no position:absolute, so they stacked in normal flow at the top-left and the checker (correctly) reported the title and axis labels as occluded by chips that were nowhere near them in the design. Adding position:absolute to the five classes fixed the geometry and contrast went to 87/87 in the same pass. One real collision remained — the MULTIMODAL chip genuinely overlaps the end line's box — fixed by fading the chips out just before the end slam, and the 15px axis/month labels were raised to 19px to clear the type floor.
Original prompt (shared by creator)TestedCommunity
@nummanali's LLM progression timeline — community prompt (tested)
Shared prompt: collected in the MIT-licensed awesome-opus5-5-videos repository, which invites anyone to copy a prompt and run it with their own agent; the prompt itself is credited to its author, @nummanali. Our video is an independent test run of that prompt — the creator does not endorse Motion Prompt Lab.
Banned list —Beat grid —Build method —Self-review —
Can you make me a video of LLM progression, like models that is from January of this year up until now, and what the trajectory is looking like, the capabilities and models as well? Like the capabilities of models too? I want to make it really like bang, bang, boom, whoa, here we go, kind of amazing innovation. Are you ready for this kind of thing? I think you'd use vMotion, 3GS, a bunch of stuff you've got. Use whatever you want.
Use this prompt
Paste into: Your AI coding agent (Claude Code, Cursor, …)
Heads up: this prompt writes code. It renders inside a coding agent — pasting it into Veo, Google Flow or Kling will not work.
Copy the prompt into your AI coding agent and let it build the project.
Swap the sample content for your own where the prompt marks it.
Render the video — or skip the prompt and open the downloaded project files in HyperFrames directly.
The prompt asks for the year in models 'bang, bang, boom' — our run answers with a capability curve across a Jan→Dec axis: twelve bars accelerating upward, a trajectory line chasing them, and five milestone chips slamming in with tightening pacing (chat → reasoning → agents → multimodal → long-horizon) before the arrow overshoots the top of the chart and the end line lands: 'WHOA — HERE WE GO'. Disclosed changes: the milestones use generic capability-era labels, not real model names, and the curve is an illustrative index (labelled as such on screen), not measured benchmark data.