AI Agents and Long Context Windows with Mark Huang

AI Agents and Long Context Windows with Mark Huang

Author: Software Huddle June 18, 2024 Duration: 50:24
Today we have Mark Huang on the show. Mark has previously held roles in Data Science and ML at companies like Box and Splunk and is now the co-founder and chief architect of Gradient, an enterprise AI platform to build and deploy autonomous assistants. In our chat, we get into some of the stuff he’s seeing around autonomous AI agents and why people are so excited about that space. Mark and his team has also recently been working on a project to extend the Llama-3 context window. They were able to extend the model from 8K tokens all the way to 1 million through a technique called theta-scaling. He walks us through the details of this project and how longer context windows will impact the types of use cases we can serve with LLMs. Follow Mark: https://x.com/markatgradient Follow Sean: https://x.com/seanfalconer

Every week on Software Huddle, Alex DeBrie and Sean Falconer sit down with a different expert from across the tech landscape. The conversations are less about quick tips and more about substantive discussions, digging into the real challenges and decisions behind building software, launching products, and navigating the industry's constant shifts. You'll hear from practitioners who have been in the trenches, offering perspectives that blend deep technical knowledge with hard-won business and entrepreneurial experience. Alex brings his specialized expertise as the author of The DynamoDB Book and an AWS Data Hero, while Sean contributes a unique viewpoint shaped by over two decades as an engineer, founder, and marketing executive, recognized as a Snowflake Data Superhero. Together, they create a space where complex topics in software development and technology trends become accessible and genuinely engaging. This podcast is for anyone who wants to move beyond surface-level news and understand the "why" behind the tools and strategies shaping our digital world. Tune in for a thoughtful huddle that feels more like a candid conversation between colleagues than a formal interview.
Author: Language: en-us Episodes: 79

Software Huddle
Podcast Episodes
It's time to build Jarvis with Kent C. Dodds [not-audio_url] [/not-audio_url]

Duration: 1:21:17
Today we have the excellent Kent C. Dodds on the program. Kent is an amazing teacher in the web development space, and I've learned a ton from him about React, JavaScript testing, and general web dev. Lately, Kent has be…
Rewriting in Rust + Being a Learning Machine with AJ Stuyvenberg [not-audio_url] [/not-audio_url]

Duration: 1:21:36
Today's guest is AJ Stuyvenberg, a Staff Engineer at Datadog working on their Serverless observability project. He had a great article recently about how they rewrote their AWS Lambda extension in Rust. It's a really int…
Software Reliability Agents with Amal Kiran [not-audio_url] [/not-audio_url]

Duration: 51:07
So if you're writing code or keeping systems running, you probably know the drill. Late night pages, chasing down weird bugs, dealing with alert storms. It's tough! It costs money when things break, and honestly, nobody…
From ORM to Infra: Prisma Postgres with Søren Bramer Schmidt [not-audio_url] [/not-audio_url]

Duration: 1:02:22
Today we have Søren from Prisma on the show. Prisma has been the most popular ORM in the TypeScript world for a while, and now they’re moving more into hosted infrastructure. We spend a lot of time talking about their ne…
Fast Inference with Hassan El Mghari [not-audio_url] [/not-audio_url]

Duration: 53:06
Today we have Hassan back on the show. Hassan was one of our first guests for Huddle when he was working at Vercel, but since then, he's joined Together AI, one of the hottest companies in the world. They just raised a m…
Seattle Startups, AI’s Future & Big Acquisitions with Yujian Tang [not-audio_url] [/not-audio_url]

Duration: 1:02:54
Today on the show, we talked with Yujian Tang. He was on the show previously when he worked at Zilliz, when we talked about vector databases and RAG. He's since branched out on his own, building the tech startup scene in…
Faster & Cheaper on PlanetScale Metal with Sam Lambert [not-audio_url] [/not-audio_url]

Duration: 1:19:43
Today, we have Sam Lambert back on the show! Sam is the CEO of PlanetScale, and if you follow him on X, you know he’s one of the sharpest voices in the database space—cutting through the hype with deep experience and a n…
Redis but Faster With Roman Gershman [not-audio_url] [/not-audio_url]

Duration: 1:00:51
Redis is consistently one of the most beloved pieces of infrastructure for developers. And in the last few years, we've seen a number of new Redis-compatible projects that aim to improve on the core of Redis in some way.…