Measuring LLMs with Jodie Burchell
.NET Rocks!3 Huhti

Measuring LLMs with Jodie Burchell

How do you measure the quality of a large language model? Carl and Richard talk to Dr. Jodie Burchell about her work measuring large language models for accuracy, reliability, and consistency. Jodie talks about the variety of benchmarks that exist for LLMs and the problems they have. A broader conversation about quality digs into the idea that LLMs should be targeted to the particular topic area they are being used for - often, smaller is better! Building a good test suite for your LLM is challenging but can increase your confidence that the tool will work as expected.

Jaksot(1961)

Donald Belcham and Kyle Baley on Brownfield Applications

Donald Belcham and Kyle Baley on Brownfield Applications

Donald Belcham and Kyle Baley talk to Carl and Richard about inheriting existing (brownfield) applications. The focus of this talk is on setting up the environment before tackling the code with a special focus on testing.Support this podcast at — https://redcircle.com/net-rocks/donations

26 Kesä 20081h 8min

Smart Client Panel at TechEd 2008

Smart Client Panel at TechEd 2008

Carl and Richard interview Glenn Block, Steve Lasker, and Tim Huckaby on the state of the Smart Client.Support this podcast at — https://redcircle.com/net-rocks/donations

24 Kesä 200851min

Eric Brechner on IM Wright's Hard Code

Eric Brechner on IM Wright's Hard Code

Carl and Richard talk to Eric Brechner, the author of the book 'I. M. Wright's Hard Code', an opinion blog (and book) with a tude!Support this podcast at — https://redcircle.com/net-rocks/donations

19 Kesä 20081h 4min

Rick Strahl on AJAX and jQuery

Rick Strahl on AJAX and jQuery

Rick Strahl takes us on a tour through using jQuery to do all the heavy lifting in JavaScript.Support this podcast at — https://redcircle.com/net-rocks/donations

17 Kesä 20081h 6min

Dan and Kathleen on Kids and Computing

Dan and Kathleen on Kids and Computing

Dan Appleman and Kathleen Dollard have a lot to say about kids: computing, and programming. This is a great show for parents or anyone who works with kids.Support this podcast at — https://redcircle.com/net-rocks/donations

12 Kesä 20081h 8min

Scott Hunter on Microsoft Dynamic Data

Scott Hunter on Microsoft Dynamic Data

Carl and Richard talk with Scott Hunter on Microsoft's Dynamic Data Runtime, which provides scaffolding and dynamic data services to developers.Support this podcast at — https://redcircle.com/net-rocks/donations

10 Kesä 20081h 3min

Scott Stanfield on Deep Zoom and PhotoSynth!

Scott Stanfield on Deep Zoom and PhotoSynth!

Scott Stanfield talks about Deep Zoom, PhotoSynth, his Mix keynote, and all the cool toys he gets to play with.Support this podcast at — https://redcircle.com/net-rocks/donations

5 Kesä 20081h 13min

John Lam Updates Us on IronRuby!

John Lam Updates Us on IronRuby!

John Lam talks about his work with the DLR and Iron Ruby at Microsoft.Support this podcast at — https://redcircle.com/net-rocks/donations

3 Kesä 20081h 8min