PinnedSay Hello to ‘Her’: Real-Time AI Voice Agents with 500ms Latency, Now Open SourceVoice Mode is hands down one of the coolest features in ChatGPT, right?Aug 17, 202412Aug 17, 202412
PinnedLlama 3 Powered Voice Assistant: Integrating Local RAG with Qdrant, Whisper, and LangChainVoice-enabled AI applications will forever change how we interact with technology.May 17, 20244May 17, 20244
Making LLMs Much Smarter: Understanding Multi-Turn RAG SystemsRunning a few evaluations on Retrieval-Augmented Generation (RAG) applications reminded me of the early days in deep learning, where subtle…Jan 181Jan 181
Orchestrating AI Agents: How to Build Scalable Enterprise SystemsIn multi-agent enterprise systems, orchestration isn’t just a utility — it’s the backbone of intelligent, scalable architecture.Jan 17Jan 17
World Foundation Models Explained: The Future of AI in Robotics and SimulationPhysical AI needs two twins: a policy twin for decision making and a world twin for simulation.Jan 17Jan 17
Efficient Content Moderation for Text-to-Image Models: PromptGuard and Safety EmbeddingsIf you ever deployed an enterprise-grade GenAI application, you know that it requires more than powerful models — they demand reliable and…Jan 16Jan 16
Cars Beyond Sensors: LLMs and SenseRAG Reduce Trajectory Prediction Errors by 70%Teams building autonomous driving (AD) systems focus on better sensors and models, but in the next few years, LLM-based AD systems will…Jan 15Jan 15
Improving Real-Time Decision-Making in Strategy Games with Adaptive Reinforcement LearningFor years, the standard mantra in AI development has been to push for more complexity. Bigger models, deeper layers, and more data, but…Jan 14Jan 14
Closed-Loop Open-Ended AI Systems Are the Future: Meet DOLPHINClosed-loop open-feedback systems are the future.Jan 13Jan 13
Qwen2.5-Coder, Cosmos Tokenizer, OpenCoder, and New SentenceTransformers: Great Times for Open…I want to highlight some standout open-source advancements that have really caught my eye:Nov 13, 2024Nov 13, 2024
