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

How to test an agent on the Embodied Safety Exam without a GPU with Embodied First Exam

Run the Embodied Safety Exam, which the README lists as needing no GPU, to test agent behavior on robot tasks.

Short answer: Install Harbor as in the core exam: uv tool install --force -e . --with-executables-from harbor; then Confirm your host has Docker Engine with Compose v2 and BuildKit, since the README lists no GPU needed for Embodied Safety Exam; run the safety suite by pointing -p at its folder under tasks/: harbor run -d embodied-first-exam@all -p tasks/<safety suite folder> -a codex -m openai/gpt-6-astra. All steps.

  • Research
  • Intermediate
  • 1 hour
  • From the README
  • Codex
  • Claude Code

Who it is forA safety-minded engineer on a machine with no GPU who wants to see how a code agent handles safety-focused robot tasks.

The problemMany suites need a GPU, which blocks people who only have a CPU machine from testing agent safety on robot tasks.

The outcomeA run of the safety suite on a CPU-only host, with per-task results from the Harbor output.

What you need first

  • Linux x86_64 host with git, uv, and Docker Engine with Compose v2 and BuildKit (or rootless podman with -e podman)
  • NVIDIA driver and NVIDIA Container Toolkit for any GPU task
  • An API key for the agent's model in .env, or a ChatGPT or Claude subscription
  • Enough free disk for the benchmark images (1 to 150 GB depending on the suite)

Steps

  1. Install Harbor as in the core exam: uv tool install --force -e . --with-executables-from harbor
  2. Confirm your host has Docker Engine with Compose v2 and BuildKit, since the README lists no GPU needed for Embodied Safety Exam
  3. Run the safety suite by pointing -p at its folder under tasks/: harbor run -d embodied-first-exam@all -p tasks/<safety suite folder> -a codex -m openai/gpt-6-astra (inferred, check the README)

Prompt for your agent

In the repo mll-lab-nu/embodied-first-exam, run the Embodied Safety Exam suite with the agent codex and the model <model id> on a host without a GPU. Report which tasks passed and which failed, and any safety-related failures. Verify that no GPU was requested in the run output.

Caveat. The exact folder name for the safety suite is not given in the README excerpt, so confirm it under tasks/ before running the inferred command.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for mll-lab-nu/embodied-first-exam and "Test an agent on the Embodied Safety Exam without a GPU"

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