{"slug": "openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets", "title": "OpenAI's SWE-bench harness relies on unisolated host Docker sockets", "summary": "OpenAI's SWE-bench evaluation harness relies on unisolated host Docker sockets, according to a bug report filed against the project. The report details errors encountered while running the harness on Docker Desktop with 8 CPUs on an M3 chip and a 15.93 GB memory limit, despite 300 GB of available disk space, and states the evaluation failed to run as expected.", "body_md": "### Describe the bug\n\nRan into a few errors\n\nI am especially not sure why I get the second one, i have 15.93 gb allocated memory and 300gb space on my disk.\n\n### Steps/Code to Reproduce\n\nUsing docker desktop with 8 CPUs available (M3 chip) and 15.93gb memory limit\n\n### Expected Results\n\nevaluation is ran\n\n### Actual Results", "url": "https://wpnews.pro/news/openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets", "canonical_source": "https://github.com/SWE-bench/SWE-bench/issues/144", "published_at": "2026-09-15 08:47:54+00:00", "updated_at": "2026-09-15 09:10:01.535679+00:00", "lang": "en", "topics": ["ai-research", "developer-tools", "ai-tools"], "entities": ["OpenAI", "SWE-bench", "Docker"], "alternates": {"html": "https://wpnews.pro/news/openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets", "markdown": "https://wpnews.pro/news/openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets.md", "text": "https://wpnews.pro/news/openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets.txt", "jsonld": "https://wpnews.pro/news/openai-s-swe-bench-harness-relies-on-unisolated-host-docker-sockets.jsonld"}}