Dual‑Agent Voice UI Makes Real‑Time Apps Easy
I'm excited about voice as a UI layer for existing visual applications — where speech and screen update together. This goes well beyond voice-only use cases like call center automation. The barrier has been a hard technical tradeoff: low-latency voice models lack reliability, while agentic pipelines (speech-to-text → LLM → text-to-speech) are intelligent but too slow for conversation. Ashwyn Sharma and team at Vocal Bridge (an AI Fund portfolio company) address this with a dual-agent architecture: a foreground agent for real-time conversation, a background agent for reasoning, guardrails, and tool calls. I used Vocal Bridge to add voice to a math-quiz app I'd built for my daughter; this took less than an hour with Claude Code. She speaks her answers, the app responds verbally and updates the questions and animations on screen. Only a tiny fraction of developers have ever built a voice app. If you'd like to try building one, check out Vocal Bridge for free: https://t.co/nGrFznAMLh
Boost LLM Performance: New SGLang Course Is Live 🚀
The video announces a new online course on efficient inference with SGlang, an open‑source framework that accelerates both text and image generation. Developed in partnership with OMIS and Radix, the curriculum targets engineers and researchers looking to cut inference costs. The...
Build Memory-Aware Agents
The video announces a new training course, "Build Memory‑Aware Agents," created in partnership with Oracle and taught by Richmond Alak and Nacho Martinez. It positions memory as the missing piece that converts a stateless large language model into an agent...
Generative Adversarial Networks (GANs) Specialization
The new specialization introduces generative adversarial networks (GANs) as a cutting‑edge deep‑learning technique for creating photorealistic images and videos. It promises hands‑on implementation, allowing students to build a working GAN from day one. Instructor Sharon Joe demystifies GANs using the art‑forger and...
TensorFlow: Advanced Techniques Specialization
The new Coursera specialization, “TensorFlow: Advanced Techniques,” teaches developers how to move beyond sequential neural networks and build sophisticated models using TensorFlow’s functional API. Across four courses, learners create custom layers and loss functions, dismantle the high‑level model.fit loop to understand...
AI-Driven Safety Investigations Save Lives Through Partnership
AI for safety investigations. This will save lives. Thank you Joseph Hanna for your leadership on this and The AES Corporation for partnering with AI Fund to build this.
US Restrictions Spur Allies to Pursue Sovereign AI
U.S. policies are driving allies away from using American AI technology. This is leading to interest in sovereign AI — a nation’s ability to access AI technology without relying on foreign powers. This weakens U.S. influence, but might lead to...
Build Reusable Anthropic Agent Skills for Any Workflow
Important new course: Agent Skills with Anthropic, built with Anthropic and taught by Elie Schoppik ! Skills are constructed as folders of instructions that equip agents with on-demand knowledge and workflows. This short course teaches you how to create them...
Blocking Data Centers Harms Environment More Than Helps
Many people are fighting the growth of data centers because they could increase CO2 emissions, electricity prices, and water use. I’m going to stake out an unpopular view: These concerns are overstated, and blocking data center construction will actually hurt...
A New Course on Retrieval Augmented Generation (RAG) Is Live!
The video announces a brand‑new online course that teaches Retrieval Augmented Generation (RAG), the technique that couples large language models with external knowledge bases to boost enterprise‑grade performance. Instructor Zan Hassani explains that RAG is already powering everyday tools—from AI‑enhanced search...
Build Your First App with AI. No Coding Background Required
The video introduces a new online course by Andrew that teaches absolute beginners how to create a functional web application using generative AI. In under 30 minutes, learners describe an idea in plain English and watch the AI produce a...
Learn Claude Code Fast with Anthropic’s Short Course
Lots of buzz on Claude Code here today. This short course, created with Anthropic, is the best way to learn to use it well. Please enjoy it!
Make Your AI Agents Production-Ready with Nvidia’s NeMo Toolkit
The video introduces NVIDIA’s NeMo Agent Toolkit (NAT), an open‑source suite designed to harden AI agents for production use. Hosted by NVIDIA engineer Brian McBear, the course walks viewers through transforming a proof‑of‑concept chatbot into a reliable, scalable service, emphasizing...
Build a Highly Autonomous Yet Unreliable Agent in Minutes
Sharing a fun recipe for building a highly autonomous, moderately capable, and very UNreliable agent using the open source aisuite package that Rohit Prasad and I have been working on. With a few lines of code, you can give a frontier...
Build a Playful Autonomous LLM Agent in Minutes
Sharing a fun recipe for building a highly autonomous, moderately capable, and very UNreliable agent using the open source aisuite package that Rohit Prasad and I have been working on. With a few lines of code, you can give a...