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(1953)

Rocky Lhotka and Anthony Handley on WPF

Rocky Lhotka and Anthony Handley on WPF

Carl meets up with Rocky Lhotka and his associate, Anthony Handley, at ReMix in Boston to discuss the work they have done separating the roles of designer and developer using WPF.Support this podcast at — https://redcircle.com/net-rocks/donations

18 Okt 20071h 10min

Dino Esposito on AJAX Architecture

Dino Esposito on AJAX Architecture

Carl and Richard caught up with Dino Esposito at DevReach in Sofia, Bulgaria to talk about AJAX architecture.Support this podcast at — https://redcircle.com/net-rocks/donations

16 Okt 20071h 10min

WPF Panel Discussion

WPF Panel Discussion

Carl and Richard host a panel discussion on Windows Presentation Foundation at DevReach in Sofia Bulgaria. Panelists: Tim Huckaby, Brian Noyes, and Todd Anglin. Chad Hower made a cameo appearance as well.Support this podcast at — https://redcircle.com/net-rocks/donations

11 Okt 20071h 12min

Ken Getz on VSTO and Other Stuff (tm)

Ken Getz on VSTO and Other Stuff (tm)

Ken Getz checked in to talk about the latest in VSTO, and then the converstaion turned geeky.Support this podcast at — https://redcircle.com/net-rocks/donations

9 Okt 20071h 16min

Eli Lopian Discusses TypeMock.NET

Eli Lopian Discusses TypeMock.NET

Carl and Richard talk to Eli Lopian about how mocking the right way can produce isolation in your test environment, allowing for more effective unit testing.Support this podcast at — https://redcircle.com/net-rocks/donations

4 Okt 200759min

Venkat Subramanium on the Inevitibility of Dynamic Languages

Venkat Subramanium on the Inevitibility of Dynamic Languages

Venkat shares his passionate reasoning as to why dynamic languages (with good unit tests) are the way of the future.Support this podcast at — https://redcircle.com/net-rocks/donations

2 Okt 20071h 3min

Mike Griffin on EntitySpaces

Mike Griffin on EntitySpaces

Mike Griffin, creator of MyGeneration and EntitySpaces, talks with Carl and Richard about EntitySpaces, a persistence layer and business object system for the Microsoft .NET 2.0 Framework, as well as his experiences with LINQ and other technologies.Support this podcast at — https://redcircle.com/net-rocks/donations

27 Sep 20071h 6min

Jack Herrington on Browser Coding

Jack Herrington on Browser Coding

Jack Herrington talks browser coding: everything from JavaScript to Flash to Silverlight, if it's done in the browser Jack does it. He brings his experiences from Macromedia to the discussion, but make no mistake. Jack loves .NET!Support this podcast at — https://redcircle.com/net-rocks/donations

25 Sep 20071h 9min

Populärt inom Teknik

uppgang-och-fall
rss-racevecka
elbilsveckan
market-makers
svd-tech-brief
natets-morka-sida
rss-uppgang-och-fall
har-vi-akt-till-mars-an
skogsforum-podcast
solcellskollens-podcast
bilar-med-sladd
rss-technokratin
bli-saker-podden
hej-bruksbil
rss-digitala-influencer-podden
rss-veckans-ai
rss-elektrikerpodden
developers-mer-an-bara-kod
rss-office-365-podden
rss-en-ai-till-kaffet