News
Voice for AI Agents and Applications
4+ hour, 55+ min ago (370+ words) Stop watching the terminal. Teach your agent to call you when it matters. Join the 7-Day Voice AI Builder Challenge. Sign-up for the waitlist! Earn an accomplishment with PRO Implement three types of voice-enabled AI applications: a voice-interactive game, a…...
Fast & Efficient LLM Inference with v LLM
2+ week, 4+ day ago (211+ words) " New Course! Enroll in AI Agents for Image and Video Generation Earn an accomplishment with PRO Apply quantization to shrink a model's memory footprint, then measure the accuracy tradeoff. Serve a model with v LLM and see how efficiently it…...
Speak With AI Andrew! | AI News & Insights
1+ mon, 1+ day ago (122+ words) " New course! Enroll in Transformers in Practice We've been working on AI Andrew, an AI companion shaped by my personality. I invite you to'try it out! Reflecting on my beliefs about how to communicate has been an interesting exercise. I…...
Data Points: How Anthropic aligns its models
1+ mon, 5+ day ago (264+ words) " New course! Enroll in Build Interactive Agents with Generative UI In today's edition of Data Points, you'll learn more about: Open AI refreshes its audio models, establishing a new SOTA Hermes now beats Open Claw in total usage among "claw-like…...
Build Interactive Agents with Generative UI
1+ mon, 1+ week ago (295+ words) " New course! Enroll in Build Interactive Agents with Generative UI Earn an accomplishment with PRO Understand the three approaches to building agent interfaces on the Generative UI Spectrum: Controlled, Declarative, and Open-Ended Gen UI, and when to use each. Build…...
Researchers at UT-Austin and Google Model Human Decision-Making in Rock-Paper-Scissors
1+ mon, 2+ week ago (21+ words) While large language models can behave in human-like ways, the similarities are superficial. A simple strategy game revealed clear differences. .....
Building Multimodal Data Pipelines
1+ mon, 3+ week ago (252+ words) " New course! Enroll in Building Multimodal Data Pipelines Extract structured, queryable information from unstructured images, audio, and video using OCR, Automatic Speech Recognition (ASR), and Vision Language Models (VLMs). Build a VLM-backed pipeline that reasons across video frames to generate…...
Understanding and Applying Text Embeddings
1+ mon, 3+ week ago (247+ words) " New course! Enroll in Spec-Driven Development with Coding Agents Instructors: Nikita Namjoshi, Andrew Ng Earn an accomplishment with PRO Use text embeddings to capture the meaning of sentences and paragraphs Apply text embeddings for tasks like text clustering, classification, and…...
Building Multimodal Search and RAG
1+ mon, 3+ week ago (289+ words) " New course! Enroll in Spec-Driven Development with Coding Agents Earn an accomplishment with PRO Learn how multimodality works by implementing contrastive learning, and see how it can be used to build modality-independent embeddings for seamless any-to-any retrieval. Build multimodal RAG…...
Evaluating and Debugging Generative AI
1+ mon, 3+ week ago (237+ words) " New course! Enroll in Spec-Driven Development with Coding Agents Earn an accomplishment with PRO Learn to evaluate programs utilizing LLMs as well as generative image models using platform-independent tools Instrument a training notebook, and add tracking, versioning, and logging Implement…...