METR Reports Week-Long AI Task Horizons
AI summary
AI nonprofit METR reported that recent models, including OpenAI’s GPT-6 Astra, can complete tasks that would take a human around a full work week. METR said measured AI capabilities have continued doubling every 3.6 months. A separate MIT Technology Review report said METR expanded its time-horizon analysis to include judgment-heavy tasks and found that some capabilities continue improving exponentially, while models lag at designing AI evaluations.
In-depth insight
METR’s analysis shows that AI systems can now handle substantially longer tasks in its evaluations, while also identifying evaluation design as an area where models still lag.
This source provides an excerpt. Continue reading on the original site.