AI Agents
AI Agent technology and applications
Articles
Prior Labs Releases TabPFN-3.5: A Tabular Foundation Model Thatโญ8
Prior Labs' TabPFN-3.5 tabular foundation model beats the winning 2015 Otto Kaggle solution using default settings, topping seven benchmarks without per-dataset...
Nums AI Releases Causilo: A Tabular Foundation Model That Topsโญ9
Nums AI releases Causilo, a pretrained tabular foundation model that leads TabArena's Elo rankings among single models for classification and regression.
Inside NVIDIA's cuDNN Graph API: Fusion, Autotuning, and Planโญ9
Explore NVIDIA's cuDNN Graph API with the Frontend: fusion, autotuning, FP8 epilogues, attention, plan reuse, serialization, and CUDA graph capture on Colab.
Google Launches Gemini 3.8 Live and Gemini 3.8 Live Extendedโญ9
Google launches Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, native speech-to-speech models for production-grade voice agents in the Gemini Live API a...
Agent-net Open Sources Webagent: A Go Harness That Turns Anyโญ9
Agent-net open sources Webagent, a Go harness that turns any website into a guarded, pluggable AI agent with Slack, WhatsApp, and HTTP support under Apache 2.0.
Agent Harness vs Agent Framework vs MCP: Which Layer Owns theโญ9
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 Backpropagationโญ8
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 Humanโญ9
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 AIโญ9
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 Backingโญ7
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 ...