An Agentic Mixture of Experts for DevOps with Sunil Mallya - #708

An Agentic Mixture of Experts for DevOps with Sunil Mallya - #708

Today we're joined by Sunil Mallya, CTO and co-founder of Flip AI. We discuss Flip’s incident debugging system for DevOps, which was built using a custom mixture of experts (MoE) large language model (LLM) trained on a novel "CoMELT" observability dataset which combines traditional MELT data—metrics, events, logs, and traces—with code to efficiently identify root failure causes in complex software systems. We discuss the challenges of integrating time-series data with LLMs and their multi-decoder architecture designed for this purpose. Sunil describes their system's agent-based design, focusing on clear roles and boundaries to ensure reliability. We examine their "chaos gym," a reinforcement learning environment used for testing and improving the system's robustness. Finally, we discuss the practical considerations of deploying such a system at scale in diverse environments and much more. The complete show notes for this episode can be found at https://twimlai.com/go/708.

Avsnitt(781)

Spatiotemporal Data Analysis with Rose Yu - #508

Spatiotemporal Data Analysis with Rose Yu - #508

Today we’re joined by Rose Yu, an assistant professor at the Jacobs School of Engineering at UC San Diego.  Rose’s research focuses on advancing machine learning algorithms and methods for analyzing ...

9 Aug 202132min

Parallelism and Acceleration for Large Language Models with Bryan Catanzaro - #507

Parallelism and Acceleration for Large Language Models with Bryan Catanzaro - #507

Today we’re joined by Bryan Catanzaro, vice president of applied deep learning research at NVIDIA. Most folks know Bryan as one of the founders/creators of cuDNN, the accelerated library for deep neu...

5 Aug 202150min

Applying the Causal Roadmap to Optimal Dynamic Treatment Rules with Lina Montoya - #506

Applying the Causal Roadmap to Optimal Dynamic Treatment Rules with Lina Montoya - #506

Today we close out our 2021 ICML series joined by Lina Montoya, a postdoctoral researcher at UNC Chapel Hill.  In our conversation with Lina, who was an invited speaker at the Neglected Assumptions in...

2 Aug 202154min

Constraint Active Search for Human-in-the-Loop Optimization with Gustavo Malkomes - #505

Constraint Active Search for Human-in-the-Loop Optimization with Gustavo Malkomes - #505

Today we continue our ICML series joined by Gustavo Malkomes, a research engineer at Intel via their recent acquisition of SigOpt.  In our conversation with Gustavo, we explore his paper Beyond the P...

29 Juli 202150min

Fairness and Robustness in Federated Learning with Virginia Smith -#504

Fairness and Robustness in Federated Learning with Virginia Smith -#504

Today we kick off our ICML coverage joined by Virginia Smith, an assistant professor in the Machine Learning Department at Carnegie Mellon University.  In our conversation with Virginia, we explore he...

26 Juli 202136min

Scaling AI at H&M Group with Errol Koolmeister - #503

Scaling AI at H&M Group with Errol Koolmeister - #503

Today we’re joined by Errol Koolmeister, the head of AI foundation at H&M Group. In our conversation with Errol, we explore H&M’s AI journey, including its wide adoption across the company in 2016, an...

22 Juli 202141min

Evolving AI Systems Gracefully with Stefano Soatto - #502

Evolving AI Systems Gracefully with Stefano Soatto - #502

Today we’re joined by Stefano Soatto, VP of AI applications science at AWS and a professor of computer science at UCLA.  Our conversation with Stefano centers on recent research of his called Gracefu...

19 Juli 202149min

ML Innovation in Healthcare with Suchi Saria - #501

ML Innovation in Healthcare with Suchi Saria - #501

Today we’re joined by Suchi Saria, the founder and CEO of Bayesian Health, the John C. Malone associate professor of computer science, statistics, and health policy, and the director of the machine le...

15 Juli 202145min

Populärt inom Politik & nyheter

svenska-fall
aftonbladet-krim
p3-krim
fordomspodden
rss-krimstad
motiv
flashback-forever
aftonbladet-daily
blenda-2
rss-sanning-konsekvens
rss-krimreportrarna
rss-vad-fan-hande
olyckan-inifran
svd-ledarredaktionen
rss-frandfors-horna
spar
rss-flodet
dagens-eko
krimmagasinet
politiken