{"slug": "the-most-misunderstood-graph-in-ai-just-got-a-major-update", "title": "The most misunderstood graph in AI just got a major update", "summary": "METR's updated time-horizon report finds that some AI capabilities are still improving along an exponential trajectory, but also indicates models are not as good at tasks requiring judgment as they are at coding. The AI evaluation nonprofit's update tracks how long a task an AI model can complete autonomously.", "body_md": "A new report from the AI evaluation nonprofit METR finds that some AI capabilities are continuing to improve along an exponential trajectory—but it also indicates that models aren’t quite as good at tasks that require judgment as they are at coding. The report is an update to the organization’s time", "url": "https://wpnews.pro/news/the-most-misunderstood-graph-in-ai-just-got-a-major-update", "canonical_source": "https://aiflash.com/news/155098/", "published_at": "2026-11-20 18:30:05+00:00", "updated_at": "2026-11-20 18:42:58.478674+00:00", "lang": "en", "topics": ["ai-research", "ai-safety", "large-language-models", "artificial-intelligence"], "entities": ["METR"], "also_reported_by": [], "takeaway": "METR's update finds AI task-completion time horizons continue to grow exponentially, yet models lag on judgment-heavy tasks relative to coding.", "recommendation": {"advice": "When evaluating models, test judgment-heavy tasks separately from coding; METR's update shows capability gains on coding do not transfer evenly to tasks requiring judgment.", "playbook": "evals-testing", "playbook_url": "https://wpnews.pro/playbooks/evals-testing"}, "alternates": {"html": "https://wpnews.pro/news/the-most-misunderstood-graph-in-ai-just-got-a-major-update", "markdown": "https://wpnews.pro/news/the-most-misunderstood-graph-in-ai-just-got-a-major-update.md", "text": "https://wpnews.pro/news/the-most-misunderstood-graph-in-ai-just-got-a-major-update.txt", "jsonld": "https://wpnews.pro/news/the-most-misunderstood-graph-in-ai-just-got-a-major-update.jsonld"}}