In this tutorial, we build a Groq-powered agentic research workflow that runs directly using Groq’s free OpenAI-compatible inference endpoint. We configure LangChain’s ChatOpenAI interface to work with Groq by setting the Groq API key and base URL, allowing us to use fast hosted models such as llama-3.3-70b-versatile for tool-based reasoning. We then connect the model […]
Every lottery ticket printed is a forecast – and when that forecast is wrong, the consequences are immediate. “If the ticket’s there, you buy it. If the display is empty, you walk away,” said Kyle Gray, Insights and Analytics Manager at the North Carolina Education Lottery. “That moment is forecasting.” […] The post Forecasting accuracy
Forecasting accuracy improves 5.9% at North Carolina Education Lottery Read More »
If you’ve ever watched a motion capture system struggle with a person’s fingers, or seen a segmentation model fail to distinguish teeth from gums, you already understand why human-centric computer vision is hard. Humans are not just objects, they come with articulated structure, fine surface details, and enormous variation in pose, clothing, lighting, and ethnicity.
For decades, supply chain software has been defined by tools — forecasting tools, optimization tools, scenario tools, dashboards, and planning applications. Each is designed to perform a specific task well. But as supply chains become more volatile and tightly coupled, the biggest challenge is no longer analytical sophistication. It’s coordination. […] The post From Tools
From Tools to Agents: How orchestrated decision intelligence is reshaping S&OP Read More »
DeepSeek-AI has released a preview version of the DeepSeek-V4 series: two Mixture-of-Experts (MoE) language models built around one core challenge making one-million-token context windows practical and affordable at inference time. The series consists of DeepSeek-V4-Pro, with 1.6T total parameters and 49B activated per token, and DeepSeek-V4-Flash, with 284B total parameters and 13B activated per token.
Training frontier AI models is, at its core, a coordination problem. Thousands of chips must communicate with each other continuously, synchronizing every gradient update across the network. When one chip fails or even slows down, the entire training run can stall. As models scale toward hundreds of billions of parameters, that fragility becomes increasingly untenable.
For all the progress made in AI agent development over the past few years, one fundamental problem has remained largely unsolved: most people never actually interact with agents. They live behind developer dashboards, inside specialized apps that users are asked to download, and within chat interfaces that the majority of the world’s population will never
Single-use plastics are a persistent source of environmental pollution, and the need to house a growing global population puts increasing pressure on resources such as timber. MIT engineers have an idea that could make a dent in both problems at once. In a recent study, a team led by mechanical engineering professor David Hardt, SM
The new word in home construction could be “plastics” Read More »
Brenda Schafer Kennedy, SM ’93, knows that sometimes the best medicine comes with four legs and fur. Kennedy is the chief veterinary and research officer for Canine Companions, a California-based, nationwide organization that provides assistance dogs at no cost to children, veterans, and adults with disabilities. “The need is enormous: One in four people in
Caring for service dogs Read More »
If you’ve been to an eye doctor and had an image taken of the inside of your eye, chances are good it was done with optical coherence tomography (OCT)—a technology invented by clinician-scientist David Huang ’85, SM ’89, PhD ’93, and now used in 40 million procedures per year. OCT is a noninvasive technique used
Inventor recalls eye imaging breakthrough Read More »
