AI Labs Say Their Models Are Speeding Up AI Research
METR estimates Anthropic's benchmark progress has nearly doubled in pace. OpenAI reports higher estimated task-success rates without human intervention, with wide variation by task.
By: The Defiant •
AI
METR estimates Anthropic's benchmark progress has nearly doubled in pace. OpenAI reports higher estimated task-success rates without human intervention, with wide variation by task.
Loading this article…





