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(1956)

Anders Hejlsberg blows our minds!

Anders Hejlsberg blows our minds!

Carl and Richard talk to Anders Hejlsberg about languages, LINQ internals, high-levels of abstraction, VB, and a few other goodies. Not to be missed!Support this podcast at — https://redcircle.com/net-rocks/donations

13 Apr 201055min

Jim Zimmerman combines Facebook and Azure

Jim Zimmerman combines Facebook and Azure

Jim Zimmerman talks about the Windows Azure Toolkit for Facebook.Support this podcast at — https://redcircle.com/net-rocks/donations

8 Apr 201056min

Charlie Kindel on Windows Phone 7

Charlie Kindel on Windows Phone 7

Carl and Richard talk to Charlie Kindel from Microsoft about building applications for the Windows Phone 7 platform.Support this podcast at — https://redcircle.com/net-rocks/donations

6 Apr 20101h

Lino Tadros goes Old School on us.

Lino Tadros goes Old School on us.

Lino Tadros of Borland and Falafel Software fame takes us back to when he worked for Anders Hejlsberg at Borland. Good stories from an old-school geek!Support this podcast at — https://redcircle.com/net-rocks/donations

1 Apr 201050min

Roman Rubin and Venkatesh Ramakrishnan Push the Limits of Silverlight.

Roman Rubin and Venkatesh Ramakrishnan Push the Limits of Silverlight.

Roman Rubin and Venkatesh (Venky) Ramakrishnan talk about their experiences architecting and building large-scale Silverlight applications.Support this podcast at — https://redcircle.com/net-rocks/donations

30 Mars 20101h 2min

Weyer and Rammer Program iPhones with MonoTouch

Weyer and Rammer Program iPhones with MonoTouch

Christian Weyer and Ingo Rammer from Thinktecture talk with Carl and Richard about programming iPhone applications with MonoTouch, an open source iPhone development tool based on Mono.Support this podcast at — https://redcircle.com/net-rocks/donations

25 Mars 201053min

Mark Brown Introduces Us to the Web Platform Installer

Mark Brown Introduces Us to the Web Platform Installer

Mark Brown talks about the Web Platform Installer, a free tool for developers from Microsoft that will sucessfully install everything your PC needs to develop web applications on the Microsoft platform.Support this podcast at — https://redcircle.com/net-rocks/donations

23 Mars 201057min

Instrumenting Applications with Runtime Intelligence

Instrumenting Applications with Runtime Intelligence

Carl and Richard talk to Gabriel Torok and Joe Kuemerle about what it takes to really know what's going on in your enterprise in real time.Support this podcast at — https://redcircle.com/net-rocks/donations

18 Mars 201057min

Populärt inom Teknik

uppgang-och-fall
elbilsveckan
rss-racevecka
market-makers
svd-tech-brief
skogsforum-podcast
natets-morka-sida
rss-elektrikerpodden
bli-saker-podden
har-vi-akt-till-mars-an
rss-uppgang-och-fall
developers-mer-an-bara-kod
rss-technokratin
bilar-med-sladd
solcellskollens-podcast
garagehang
ai-sweden-podcast
bosse-bildoktorn-och-hasse-p
rss-bakom-boken
rss-veckans-ai