DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to plan a video-to-Blender world program evaluation with Awesome Code as X

Use PhysCodeGym to test whether a coding agent rebuilds a video as a physical Blender scene.

Short answer: Read the World programs and Benchmark definitions in the README to confirm what a world program is; then open the PhysCodeGym GitHub repository at github.com/ShaoShuai0605/PhysCodeGym; open the dataset at huggingface.co/datasets/ShaoShuai0605/PhysCodeGym and choose one video. All steps.

  • Research
  • Advanced
  • PT3H
  • From the README
  • Any agent

Authorization notice. Awesome Code as X is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA graphics or simulation engineer who wants to test whether generated scene code keeps the physics of a real video.

The problemReconstructions from video often look right but break physics, and it is hard to check this automatically.

The outcomeA short evaluation plan that uses the PhysCodeGym repository and dataset to check a reconstructed Blender program against the physics of its video.

What you need first

  • A web browser to open the linked papers and project pages
  • Basic familiarity with robot manipulation or simulation terms
  • For reproduction: a GitHub account, git, and the hardware or simulator that a chosen project requires (the list does not state these)

Steps

  1. Read the World programs and Benchmark definitions in the README to confirm what a world program is.
  2. Open the PhysCodeGym GitHub repository at github.com/ShaoShuai0605/PhysCodeGym.
  3. Open the dataset at huggingface.co/datasets/ShaoShuai0605/PhysCodeGym and choose one video.
  4. Ask a coding agent to write a Blender program for that video, then run the physics check described in the PhysCodeGym repository.

Prompt for your agent

Using the PhysCodeGym entry in the kkakkkka/awesome-code-as-x README, write a plan to evaluate a coding agent that rebuilds <video name> as an executable Blender program. Expected output: a numbered plan with the dataset link, the agent steps, and the physics check to run. Verify that the plan uses only the linked repository and dataset.

Caveat. PhysCodeGym is listed only as a benchmark name with links, so the exact physics check and run commands must come from its repository.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for kkakkkka/awesome-code-as-x and "Plan a video-to-Blender world program evaluation"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer