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)

Tim Sneath and Ian Ellison-Taylor on Windows Past, Present and Future

Tim Sneath and Ian Ellison-Taylor on Windows Past, Present and Future

Carl and Richard talk to Windows veterans Tim Sneath and Ian Ellison-Taylor about the olden days of Windows, how it has evolved, and how it may look in the future from a developer perspective.Support this podcast at — https://redcircle.com/net-rocks/donations

15 Nov 20071h 7min

Pablo Castro on Astoria

Pablo Castro on Astoria

Pablo Castro from the SQL Server Product Group at Microsoft talks about his work with Astoria, an infrastructure for bringing web technologies and data sources together. Astoria uses the Entity Framework, which Pablo is also involved with.Support this podcast at — https://redcircle.com/net-rocks/donations

13 Nov 20071h 11min

Mark Dunn at TechEd Asia

Mark Dunn at TechEd Asia

We sent Mark to sit down with and interview the minds behind TechEd Asia.Support this podcast at — https://redcircle.com/net-rocks/donations

7 Nov 20071h 11min

Sue Mosher On Outlook

Sue Mosher On Outlook

Sue Discusses her work in Outlook and Exchange issues as well as the coding of Outlook and the new features of Outlook 2007.Support this podcast at — https://redcircle.com/net-rocks/donations

6 Nov 20071h 7min

Nikhil Kothari on Facebook.NET and Everything Else!

Nikhil Kothari on Facebook.NET and Everything Else!

Nikhil Kothari talks about his eperiences working at Microsoft on all things web, including ASP.NET controls and Facebook.NET. Just read his bio to see where we took this conversation.Support this podcast at — https://redcircle.com/net-rocks/donations

1 Nov 20071h 4min

David Yack Talks Microsoft CRM!

David Yack Talks Microsoft CRM!

David Yack introduces us to Microsoft CRM and related products, giving us the developer story.Support this podcast at — https://redcircle.com/net-rocks/donations

30 Okt 20071h 5min

Catching up with Brad Abrams

Catching up with Brad Abrams

Carl and Richard talk to Brad Abrams about Silverlight +Next and WPF.Support this podcast at — https://redcircle.com/net-rocks/donations

25 Okt 20071h 6min

Alex Daley on Windows Live Labs

Alex Daley on Windows Live Labs

Carl and Richard talk to Alex Daley about some of the projects he's working on at Windows Live Labs, a division of Microsoft Research that focuses on shipping new web technologies.Support this podcast at — https://redcircle.com/net-rocks/donations

23 Okt 20071h 11min

Populärt inom Teknik

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