Results for “learning-log”

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak retrievals) → handoff (durable snapshot if session-ending). Use when the work involves "what did we decide", "remember this", "save where we are", or any closing checkpoint.

Design an adaptive assessment loop where each student response triggers the next instructional move. Use when building technology-enhanced formative assessment cycles.

Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), and distributed training (DDP, FSDP, DeepSpeed) for scalable neural network training.