Sam Witteveen

Gemini Live Avatars

Gemini 3.8 Flash TTS with Voice Cloning

Nemotron 3 Diarization - Who Said That?

Pronto

How to Build Things with Jev & OpenJevs

Open Jev Models Are Here!!

Jev - The Ultimate Classification Model?

The OpenSource Managed Agents

Pronto

Managed Agents - Don't Get Locked In

MiniCPM5-2B: The Best Sub-Agent Model Yet?

NVIDIA Doubles Down on Local AI With PAIR

BreezeTTS2 - 100% Local Real-Time Voice

GLM 5.3 Flash vs GLM 5.3: When Cheaper Is the Right Call

Docker Sandboxes - Safe and Secure Agents

Pronto

Qwen3.8-27B & How to Serve it Fast

Nemotron Lightning - NVIDIA's Super Fast Agent MoE

Switchyard NVIDIA's Local Agent Router

Meta's Open Weight - Muse Glimmer 30B

ThinkingCap - The Local Coding Model

AMD Ryzen AI Halo - 100% Local AI

Cactus Needle - The 26M Function Calling Model

Hy3 from Tencent - The NEW GLM Competitor

MiniCPM5 - Just How Good Can a 1B Model Be?

Introducing the Gemini Omni Flash API

Introducing Ornith 1.0 - Agentic Coding LLMs

Qwen-AgentWorld The World Model for Agents

VibeThinker 3B - Taking on Giant Models

GLM 5.2 - The Top NEW Open Weights Model

Mythos 5 & Fable 5 Launched

The NEW Best ASR - NVIDIA Nemotron 3.5 ASR

Nemotron 3 Ultra NVIDIA's Beast Model

Cosmos 3 - NVIDIA's World Foundation Model

Running Local AI on AMD

OpenShell Agents

MiniCPM-V 4.6: The Tiny Vision Model Your Agents Need

Granite 4.1 - The Fastest ASR?

How Claude's Design Agents Work

NVIDIA's NEW All-in-One: Nemotron 3 Nano Omni for Multimodal Agents

The Era of Agents is Here: Logan Kilpatrick on Why Everyone Is Now a Builder

Must Haves For Agents in Production

Muse Spark - Meta's NEW Llama Replacement

Gemma 4 Has Landed!

Agent Skills: Code Beats Markdown (Here's Why)

LiteParse - The Local Document Parser

Building Single-User vs Multi-User Agents: What Actually Changes

Google Stitch Just Became an AI Figma (And It's Free)

NVIDIA NemoCLAW!! - GTC 2026

Gemini Embedding 2 - Audio, Text, Images, Docs, Videos