Reasoning & planning
Explores a small reasoning dataset and inference-time compute controls as a recipe for test-time scaling.
AI summary
Methods worth understanding
AI Techniques Radar
New AI methods, the evidence behind them, and how to put them to work.
Reasoning & planning
Studies reinforcement learning as a way to develop language-model reasoning without human-written reasoning trajectories.
AI summary
Retrieval & memory
Introduces a neural long-term memory component that learns during inference, alongside attention-based context processing.
AI summary