Phillip Carter, Principal Product Manager at Honeycomb and open source software developer, talks with host Giovanni Asproni about observability for large language models (LLMs). The episode explores similarities and differences for observability with LLMs versus more conventional systems. Key topics include: how observability helps in testing parts of LLMs that aren't amenable to automated unit or integration testing; using observability to develop and refine the functionality provided by the LLM (observability-driven development); using observability to debug LLMs; and the importance of incremental development and delivery for LLMs and how observability facilitates both. Phillip also offers suggestions on how to get started with implementing observability for LLMs, as well as an overview of some of the technology's current limitations. This episode is sponsored by WorkOS.
Episode 498: James Socol on Continuous Integration and Continuous Delivery (CICD)
Episode 497: Richard L. Sites on Understanding Software Dynamics
Episode 496: Bruce Momjian on Multi-Version Concurrency Control in Postgres (MVCC)
Episode 495: Vaughn Vernon on Strategic Monoliths and Microservices
Episode 494: Robert Seacord on Avoiding Defects in C Programming
Episode 493: Ram Sriharsha on Vectors in Machine Learning
Episode 492: Sam Scott on Building a Consistent and Global Authorization Service
Episode 491: Chase Kocher on The Recruiting LifeCycle
Episode 490: Tim McNamara on Rust 2021 Edition
Episode 489: Sam Boyer Package Management
Episode 488: Chris Riccomini and Dmitriy Ryaboy on the Missing Readme
Episode 487: Davide Bedin on Dapr Distributed Application Runtime
Episode 486: Bob Nystrom on Dart
Episode 485: Howard Chu on B+tree Data Structure in Depth
Episode 484: Audrey Lawrence on Timeseries Databases
Episode 483: Alexander Pugh on Robotic Process Automation
Episode 482: Luke Hoban on Infrastructure as Code
Episode 481: Ipek Ozkaya on Managing Technical Debt
Episode 480: Venky Naganathan on Chatbots
Episode 479: Luis Ceze on the Apache TVM Machine Learning Compiler
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Lex Fridman Podcast