Continual Learning: How AI Learns Without Forgetting
Continual learning lets a model absorb new tasks without catastrophic forgetting. Setups, methods, Google Nested Learning and Meta sparse memory finetuning.
Context engineering, agent swarms, verification loops: what the AI Engineer Summit revealed about how agentic coding actually works — and where the IDE is going.
Kimi K2 Thinking: Inside Moonshot AI's Agentic Reasoning Model
Kimi K2 Thinking is Moonshot AI's open reasoning agent: 200–300 tool calls, 256K context, INT4 quantization. Architecture, benchmarks, and real use cases.