TLDR Tech / AI
Dario Says Continual Learning Is Solved. Is It?
Continual learning research is aimed at breaking past the feasible horizon of current techniques. If models can't learn new things while performing tasks, they will struggle when the task horizon grows very long. Context management and other engineering improvements can push task horizons to weeks, or even months, but very long-horizon tasks remain out of reach. Human-level continual learning may be 'solved', but the revolution is not yet complete.
Read the full story