continual-learning
Macaron froze a 744B base and bolted four specialists on top News
Mind Lab released open weights for Macaron-V1, a continual-learning system that never touches its base model and instead composes small specialist adapters on top, picking exactly one per user turn.
Loss of plasticity: why a network that trains forever stops being able to learn Lesson
Keep training a neural network on a stream of new tasks and it does not just forget the old ones - it gradually loses the ability to learn new ones at all, until it performs worse than a freshly initialized network.
Catastrophic forgetting: why teaching an AI something new can erase what it knew Lesson
Catastrophic forgetting is the tendency of a neural network to lose an old skill when trained on a new one, because both skills are stored in the same weights and nothing protects the old settings.
Richard Sutton's Oak Lab bets against frozen models: a trillion-parameter agent on 20 watts News
Turing-winner Richard Sutton launched Oak Lab with a north-star goal of a trillion-parameter agent that learns and plans in real time on about 20 watts, betting on continual experiential learning over the static pre-train-then-freeze paradigm behind today's LLMs.
Macaron-V1 Tool
Open weights for a model family that freezes its base and composes specialist LoRA adapters on top, picking one per user turn. The 744B Venti flagship carries chat, agent, coding and generative-UI specialists; the 50B Tall variant runs the same design on local hardware.