Ask, build, compose: What our 5th Genie Hackathon taught us about Databricks Genie
How Databricks hackathons work We run these hackathons for a simple reason: the fastest way to learn a product is to build something with it. Each one kicks off with…
-
-
Building WeaveCLI: One Engineer’s Case Study
Most AI demos work. Most AI products don’t. This series is a collection of interviews with engineers who shipped AI agents to production, covering the stacks they chose, the architectures…
-
How to Evaluate General-Purpose Robot Policies for Real-World Deployment
Robotics foundation models have made remarkable progress. Today’s best systems can follow natural language instructions to pick, place, sort, and manipulate a wide variety of objects. But as these models…
-
Build a semantic layer for agentic AI on AWS with Stardog and Amazon Bedrock AgentCore
In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Strands…
-
Portable APIs and High-Performance Kernels for Multi-Silicon LLM Inference – PyTorch
TL;DR The TokenSpeed-kernel is a standalone, open-source subsystem designed to solve backend complexity in LLM inference. It introduces a clean, layered API and registry system that decouples the high-level runtime…
-
Graph neural networks in TensorFlow — The TensorFlow Blog
February 06, 2024 — Posted by Dustin Zelle – Software Engineer, Research and Arno Eigenwillig – Software Engineer, CoreMLThis article is also shared on the Google Research BlogObjects and their relationships…
-
Hippocratic AI partners with Modular to power flexible, high-quality inference for real-time patient conversations
Hippocratic AI builds safety-focused AI health agents that converse with patients, helping to close the global shortfall of 15 million healthcare workers. Their Polaris system orchestrates dozens of specialized models…
-
The ambulatory intelligence gap | Databricks Blog
Ambulatory care, the outpatient clinics and physician practices where most patients interact with a health system, is where growth is won or lost. Yet many health systems struggle with the…
-
Best AI Observability Tools for Agentic Systems
AI applications used to rely on a handful of straightforward LLM calls. Now agents make hundreds of decisions in response to a single user input, calling tools, retrieving context, and…
-
AI Model Co-Design: Hardware-Friendly LLM Design
AI performance comes down to three dimensions: Accuracy: How well the model reasons and produces outputs Throughput: How many tokens per second a datacenter can generate Interactivity: How responsive the…
