METR updates time horizon plot showing exponential AI improvement and judgment weaknesses
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
A new report from nonprofit METR updates its time horizon plot, revealing that AI capabilities continue growing exponentially, with model-completed tasks doubling every four months. However, the evaluation shows models remain less proficient at open-ended tasks requiring judgment compared to verifiable tasks like coding.
Continue in the app — vote & join in ➔Source: MIT Technology Review · via ahirlevel.hu