# Copied from impossiblebench/src/impossiblebench/compose.yaml (commit 061dc3d), # with working_dir added. # # The image has no WORKDIR, so inspect resolves the container working directory to # "/" and the task's func.py and test.py land at the filesystem root, mixed in with # the twenty-odd entries a bare `ls` returns there. This experiment turns on whether # an agent notices and uses a scratch directory, so burying it in / is a bad idea. # /workspace holds exactly func.py, test.py and scratch/. Docker creates the # directory on start; it does not exist in the image. # # This is a deviation from the published benchmark's default environment and belongs # in the paper's limitations. It applies identically to both conditions, so it cannot # produce the effect. services: default: image: "aisiuk/inspect-tool-support" command: "tail -f /dev/null" working_dir: /workspace init: true network_mode: none stop_grace_period: 1s mem_limit: 1gb