Architecturally, an orchestrator routes every request to one of three specialist sub-agents. Each sub-agent owns its own tools for reading or writing the memory store. First, the IngestAgent handles ...

Kimi K3 is a sparse Mixture-of-Experts (MoE) model built on two architectural updates. Those are Kimi Delta Attention (KDA) and Attention Residuals (AttnRes). Both change how information flows across ...

Inkling is a Mixture-of-Experts transformer with 975B total parameters and 41B active. It supports a context window of up to 1M tokens. Pretraining covered 45 trillion tokens of text, images, audio, ...

Domain SDK covers Vercel, Cloudflare for SaaS, Railway, Render, and Netlify. You add a hostname, show the exact DNS records, then track provider state until it is ready. It does not register domains, ...

Anthropic just shipped Claude Sonnet 5. They call it its most agentic Sonnet model yet. It plans, drives browsers and terminals, and runs autonomously across long tasks. Sonnet 5 is the default model ...

Google released LiteRT.js, a JavaScript binding of LiteRT. LiteRT is Google’s on-device inference library, previously called TensorFlow Lite. LiteRT.js runs .tflite models directly inside the browser.

gpt-realtime-2.1-mini is a mini reasoning model for realtime voice interactions. It responds to audio and text inputs over a live connection. OpenAI positions it as the faster, more cost-efficient ...

A new Cursor study reports that newer coding agents often retrieve known fixes instead of deriving them, inflating popular benchmark scores. Reward hacking means a model earns the reward without doing ...

OpenAI has opened a limited preview of GPT-5.6, a three-tier model family. It adds two new reasoning modes and a heavier safety layer. OpenAI has begun a limited preview of GPT-5.6, its ...

Ant Group’s Robbyant has released LingBot-VLA 2.0, a Vision-Language-Action (VLA) foundation model for robots. The release includes a technical report, an Apache-2.0 codebase, and a 6B checkpoint. The ...

AI scientists are becoming a new interface for scientific computing. These agents read papers, write code, generate hypotheses, call APIs, and inspect files. But science is not software engineering.

NVIDIA has released Audex (Nemotron-Labs-Audex-30B-A3B), a unified audio-text large language model. It understands and generates both audio and speech. It also keeps the text intelligence of its ...