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)

David Aiken on Bridging the Gap between Dev and IT

David Aiken on Bridging the Gap between Dev and IT

Carl and Richard talk with David Aiken about how developers can work more productively with IT professionals.Support this podcast at — https://redcircle.com/net-rocks/donations

10 Jan 20081h 10min

Steven Lees on FeedSync

Steven Lees on FeedSync

Carl and Richard talk feed synchronization with Steven Lees from Microsoft about FeedSync, a Windows Live Dev service for synchronizing RSS and Atom feeds, and FeedSync feeds across the web.Support this podcast at — https://redcircle.com/net-rocks/donations

8 Jan 200851min

Kathleen Dollard on the Evolution of Software Development

Kathleen Dollard on the Evolution of Software Development

Kathleen spends a little more than an hour talking with Richard and Carl about how software development has changed over the years, for better mostly. Still, change is difficult, and Kathleen provides some insight into how she approaches these changes.Support this podcast at — https://redcircle.com/net-rocks/donations

3 Jan 20081h 11min

Ken Levy on Visual Studio Extensibility (VSX)

Ken Levy on Visual Studio Extensibility (VSX)

Carl and Richard talk VSX with Ken Levy who these days is all about community and showing developers how to extend Visual Studio.Support this podcast at — https://redcircle.com/net-rocks/donations

1 Jan 20081h 1min

Jeff Prosise Goes Deep on Silverlight

Jeff Prosise Goes Deep on Silverlight

Carl and Richard talk Silverlight with Jeff Prosise.Support this podcast at — https://redcircle.com/net-rocks/donations

27 Dec 20071h 10min

Joe Duffy on the Task Parallel Library

Joe Duffy on the Task Parallel Library

Carl and Richard talk to Microsoft's Joe Duffy about the Task Parallel Library, which promises to make multi-threaded programming easier for us all.Support this podcast at — https://redcircle.com/net-rocks/donations

25 Dec 20071h 8min

Richard Campbell Tells All!

Richard Campbell Tells All!

It's our 300th show! Can you believe it? Carl interviews Richard, who tells many stories of his experiences in electronics and computers. Don't miss the funny stories!Support this podcast at — https://redcircle.com/net-rocks/donations

20 Dec 20071h 15min

Jeff Palermo on ASP.NET MVC

Jeff Palermo on ASP.NET MVC

Jeff Palermo introduces the nascent ASP.NET Model View Controler Framework. He easily explains the benefits, pitfalls, and techniques you can use to implement a MVC pattern in ASP.NET.Support this podcast at — https://redcircle.com/net-rocks/donations

19 Dec 20071h 5min

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