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(1954)

Michael Dirolf is SQL Free with MongoDB

Michael Dirolf is SQL Free with MongoDB

MongoDB is a non-relational database. For most of us working with SQL Server, using a non-relational database is a strange idea. Michael Dirolf makes the case.Support this podcast at — https://redcircle.com/net-rocks/donations

15 Dec 200955min

Live from Oredev 2009

Live from Oredev 2009

Carl and Richard interview today's luminaries live on stage at Oredev in Malmo, Sweden November 4th and 5th, 2009.Support this podcast at — https://redcircle.com/net-rocks/donations

10 Dec 20091h 17min

Paul Litwin on SQL Reporting Services

Paul Litwin on SQL Reporting Services

Carl and Richard caught up with Paul Litwin to talk about Reporting Services. Recorded live at DevConnections in Las Vegas last month.Support this podcast at — https://redcircle.com/net-rocks/donations

8 Dec 200954min

Codeplex Foundation

Codeplex Foundation

Carl and Richard talk to Sam Ramji and Bill Staples about the Codeplex Foundation, which provides a framework to facilitate the participation of corporate software developers in open source projects communities.Support this podcast at — https://redcircle.com/net-rocks/donations

3 Dec 200957min

Weyer and Baier on WIF

Weyer and Baier on WIF

Christian Weyer and Dominick Baier talk about real world Windows Identity Foundation. This show wraps up our three-part series on WIF.Support this podcast at — https://redcircle.com/net-rocks/donations

1 Dec 200955min

Live from PDC, it's My .NET Story!

Live from PDC, it's My .NET Story!

Carl and Richard interview seven contestants in the My .NET Story contest. Enter a story about your .NET application online at www.mydotnetstory.com. The winner gets either a trip to the Galopagos Islands or a Smart Car.Support this podcast at — https://redcircle.com/net-rocks/donations

26 Nov 20091h 34min

Bowen and Cummings on XNA

Bowen and Cummings on XNA

Carl and Richard talk to Chris Bowen of Microsoft and Michael Cummings of Magenic on using XNA to develop games and applications for the PC, XBox and Zune.Support this podcast at — https://redcircle.com/net-rocks/donations

24 Nov 200959min

It's The 500th Freakin Show!

It's The 500th Freakin Show!

I know! We can't believe it either. We went back over the last 100 shows and cherry picked a few of our favorite segments. Thank you for your continued support!Support this podcast at — https://redcircle.com/net-rocks/donations

19 Nov 20091h 7min

Populärt inom Teknik

uppgang-och-fall
rss-racevecka
elbilsveckan
market-makers
svd-tech-brief
rss-uppgang-och-fall
natets-morka-sida
skogsforum-podcast
har-vi-akt-till-mars-an
solcellskollens-podcast
rss-elektrikerpodden
developers-mer-an-bara-kod
bli-saker-podden
rss-technokratin
bilar-med-sladd
gubbar-som-tjotar-om-bilar
hej-bruksbil
rss-en-ai-till-kaffet
bosse-bildoktorn-och-hasse-p
rss-digitala-influencer-podden