AI Agents
AI Agent technology and applications
Articles
Agent Harness vs Agent Framework vs MCP: Which Layer Owns the⭐9
Harness, framework, and MCP each own different parts of agent architecture: the execution loop, state, tool transport, permissions, and recovery. Here's which l...
Sakana AI's PC-ALM: A Layer-Local Alternative to Backpropagation⭐8
Sakana AI's PC-ALM enables layer-local training of 1,000-layer networks within 2% of backpropagation on MNIST, offering a backprop-free alternative with JAX cod...
Reward AI Unveils OM-1: A Robot Policy Trained Purely on Human⭐9
Reward AI unveils OM-1, a robot manipulation policy trained purely on human demonstrations with no teleoperation or on-robot data, using a wearable sensorized g...
NVIDIA Open-Sources OSMO: One YAML Orchestrates Physical AI⭐9
NVIDIA OSMO is an open-source, Kubernetes-native orchestrator that runs physical AI workflows across training, simulation, and robot testing from a single YAML ...
Anthropic's Three-Step 'Pace the Frontier' Plan Wins Backing⭐7
Anthropic's "Pace the Frontier" plan, backed by OpenAI, xAI, and Microsoft, proposes slowing AI development. But is it too late to slow AI down? We examine the ...
Hierarchical NeRF with JAX3D: Volumetric Rendering, Novel-View⭐8
Build an end-to-end hierarchical NeRF in JAX with JAX3D: volumetric rendering, importance sampling, training, novel-view synthesis, 360° rendering, and marching...
Princeton Researcher Proposes Recurrent Looped Transformer (RLT)⭐7
Princeton's Recurrent Looped Transformer (RLT) carries decoder state and SWA cache across tokens, with no reset. A design spec for unbounded recurrent depth.
AWS Launches Pizza Bot: An Open Source Inbox for Background AI Agents⭐9
AWS Pizza Bot is an open source inbox for async AI agents, organizing completed work and pending approvals into an email-style view with scheduling and webhooks...
Context Engineering Inside the Harness: 4 Mechanisms That Beat⭐7
Long-horizon AI agents fail from context overflow and goal loss. Learn how compaction, memory, budgeting, and todo-state in the harness fix it.
GPU-Accelerated Machine Learning with NVIDIA cuML and RAPIDS:⭐9
Explore NVIDIA cuML and RAPIDS for GPU-accelerated machine learning, covering benchmarking, explainability, clustering, and model inference in this tutorial.