The New Stack Podcast12 Okt 2023

What’s Next in Building Better Generative AI Applications?

Since the release of OpenAI's ChatGPT-3 in late 2022, various industries have been actively exploring its applications. Madhukar Kumar, CMO of SingleStore, discussed his experiments with large language models (LLMs) in this podcast episode with TNS host Heather Joslyn. He mentioned a specific LLM called Gorilla, which is trained on APIs and can generate APIs based on specific tasks. Kumar also talked about SingleStore Now, an AI conference, where they plan to teach attendees how to build generative AI applications from scratch, focusing on enterprise applications.

Kumar highlighted a limitation with current LLMs - they are "frozen in time" and cannot provide real-time information. To address this, a method called "retrieval augmented generation" (RAG) has emerged. SingleStore is using RAG to keep LLMs updated. In this approach, a user query is first matched with up-to-date enterprise data to provide context, and then the LLM is tasked with generating answers based on this context. This method aims to prevent the generation of factually incorrect responses and relies on storing data as vectors for efficient real-time processing, which SingleStore enables.

This strategy ensures that LLMs can provide current and contextually accurate information, making AI applications more reliable and responsive for enterprises.

Learn more from The New Stack about LLMs and SingleStore:

Top 5 Large Language Models and How to Use Them Effectively

Using ChatGPT for Questions Specific to Your Company Data

6 Reasons Private LLMs Are Key for Enterprises

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(300)

Why MotherDuck refuses to fork DuckDB

At a recent MCP developer summit, The New Stack spoke with Till Döhmen, AI lead atMotherDuck, about the company’s growing role in the evolving DuckDB ecosystem. Backed by investors includingTomasz Tun...

27 Mai 27min

JetBrains is selling independence as the rest of AI coding picks sides

JetBrains is positioning itself as the last major independent AI coding-tool vendor in a market increasingly tied to hyperscalers and foundation model labs. Speaking at Google Cloud Next, JetBrains VP...

21 Mai 26min

Why Block handed Goose to the Linux Foundation

What began as an internal developer tool atBlockhas evolved into a broader open-source initiative with industry backing. Goose, Block’s AI coding agent, followed a path similar to Amazon’s transformat...

15 Mai 19min

Fivetran's CPO: closed data stacks won't survive the agent era

At Google Cloud Next 2026, Fivetran Chief Product Officer Anjan Kundavaram argued that enterprise data systems are unprepared for the scale of AI-driven analytics. Unlike humans, AI agents can generat...

13 Mai 22min

The new FinOps problem isn't cloud bills

At Google Cloud Next 2026, Finout co-founder and CEO Roi Ravhon and Google Cloud FinOps lead Pathik Sharma discussed how FinOps is rapidly evolving for the AI era. Ravhon argued that while cloud FinOp...

12 Mai 28min

How Microsoft is governing thousands of Kubernetes clusters without manual intervention

Managing Kubernetes at fleet scale introduces significant complexity, especially as organizations expand from a few clusters to hundreds or thousands across cloud, on-premises, and edge environments. ...

7 Mai 25min

Why long-running AI agents break on HTTP and how Ably is fixing it

In this episode ofThe New Stack Makers, Matthew O’Riordan, CEO of Ably, explains how infrastructure originally built for human collaboration is now well-suited for long-running AI agents. While Ably i...

6 Mai 31min

Why the Linux Foundation adopted MCP, with Jim Zemlin and Mazin Gilbert

Agentic AI is advancing rapidly, with open-source projects racing to keep pace with real-world deployment. To accelerate progress, the Linux Foundation consolidated key technologies—Model Context Prot...

6 Mai 32min