Measuring LLMs with Jodie Burchell

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.

Avsnitt(1974)

Catching up with Miguel de Icaza

Catching up with Miguel de Icaza

Miguel de Icaza is back to tell us what's new with the Mono project, an open source implementation of the .NET Framework based on FreeBSD with support for Windows, Mac, and Linux.Support this podcast at — https://redcircle.com/net-rocks/donations

17 Juli 20071h 10min

John Lam on the DLR

John Lam on the DLR

John Lam talks to Carl and Richard about his trek from Canada to Redmond, and his work on dynamic languages, including Ruby CLR, and the Microsoft DLR (Dynamic Language Runtime), which we may find in some future version of the .NET Framework.Support this podcast at — https://redcircle.com/net-rocks/donations

12 Juli 20071h 9min

CSLA with Rockford Lhotka

CSLA with Rockford Lhotka

Rocky talks about CSLA 3.0, the relationship with WPF and Silverlight, "paranoid" code, pblishing and his experience with ebooks.Support this podcast at — https://redcircle.com/net-rocks/donations

10 Juli 20071h 7min

The Identity Panel at TechEd 2007

The Identity Panel at TechEd 2007

In the last of the content from TechEd 2007 Carl and Richard host a panel on Identity issues with Ani Babaian, Michele Leroux Bustamante, Scott Golightly, and Richard Turner.Support this podcast at — https://redcircle.com/net-rocks/donations

5 Juli 20071h 17min

Rogers Sessions Explains Enterprise Architectures!

Rogers Sessions Explains Enterprise Architectures!

Roger Sessions talks to Carl and Richard about enterprise architecture, with a focus on dealing with software complexity.Support this podcast at — https://redcircle.com/net-rocks/donations

3 Juli 20071h 7min

Team System Panel from TechEd 2007

Team System Panel from TechEd 2007

Another great panel discussion from TechEd 2007! Carl and Richard talk to a panel of experts about various topics around VSTS and team development focusing on team challenges.Support this podcast at — https://redcircle.com/net-rocks/donations

28 Juni 20071h 4min

Box and Sells on the State of Publishing

Box and Sells on the State of Publishing

Don Box and Chris Sells talk to Carl and Richard about a myriad of things including the state of publishing, especially books.Support this podcast at — https://redcircle.com/net-rocks/donations

25 Juni 20071h 11min

Introducing Acropolis

Introducing Acropolis

Carl and Richard talk with members of the Microsoft Acropolis team at TechEd 2007. Acropolis is a software factory-ish toolset that allows business developers to develop quality line-of-business WPF applications with ease.Support this podcast at — https://redcircle.com/net-rocks/donations

21 Juni 200744min

Populärt inom Teknik

uppgang-och-fall
rss-racevecka
market-makers
elbilsveckan
bilar-med-sladd
rss-laddstationen-med-elbilen-i-sverige
rss-badfluence
natets-morka-sida
rss-uppgang-och-fall
rss-veckans-ai
skogsforum-podcast
rss-technokratin
rss-elektrikerpodden
hej-bruksbil
mediepodden
developers-mer-an-bara-kod
bli-saker-podden
gubbar-som-tjotar-om-bilar
rss-digitala-influencer-podden
rss-snacka-om-ai