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.

Episoder(1954)

Kathleen Dollard LIVE at Dev Connections Orlando 2006

Kathleen Dollard LIVE at Dev Connections Orlando 2006

Kathleen Dollard, live at Dev Connections Orlando, 2006! A great talk about the future of code generation and more.Support this podcast at — https://redcircle.com/net-rocks/donations

11 Apr 20061h 1min

Avalon, AJAX, Vista, and more with Tim Huckaby

Avalon, AJAX, Vista, and more with Tim Huckaby

Tim Huckaby talks about developing for Avalon, AJAX, and Vista in general.Support this podcast at — https://redcircle.com/net-rocks/donations

4 Apr 20061h 2min

CSLA.NET 2.0 with Rocky Lhotka

CSLA.NET 2.0 with Rocky Lhotka

Rocky Lhotka discusses his CSLA.NET application framework version 2.0. New features, changes, and migration tips.Support this podcast at — https://redcircle.com/net-rocks/donations

28 Mar 20061h 8min

Test Driven Development with Jean Paul Boodhoo

Test Driven Development with Jean Paul Boodhoo

Get some deep insight into the tools and the techniques that make Test Driven Development an important new tool for developers.Support this podcast at — https://redcircle.com/net-rocks/donations

21 Mar 20061h 9min

Security Update with Patrick Hynds

Security Update with Patrick Hynds

Pat Hynds checks in with us to talk ASP.NET security sharing his latest insights and telling stories from the field. As always, Pat brings his post-GI point of view to the conversation, which is always enjoyable.Support this podcast at — https://redcircle.com/net-rocks/donations

14 Mar 20061h 11min

Joe Duffy on Concurrency

Joe Duffy on Concurrency

Carl and Richard have an engaging conversation with Joe Duffy from the CLR team on dealing with concurrency in multi-threaded applications. Buy his books! This is great stuff!Support this podcast at — https://redcircle.com/net-rocks/donations

6 Mar 20061h 12min

Nick Landry on the State of Mobile Development

Nick Landry on the State of Mobile Development

Our old friend Nickolas Landry talks about the latest developments in mobile technology, both hardware and software, including Windows Mobile 5.0 and the Compact Framework 2.0Support this podcast at — https://redcircle.com/net-rocks/donations

28 Feb 20061h 6min

Brian Noyes on Data Binding in .NET 2.0

Brian Noyes on Data Binding in .NET 2.0

Brian Noyes talks us through data binding in .NET 2.0 from the gee-whiz draggy droppy stuff to multi-tier enterprise applications.Support this podcast at — https://redcircle.com/net-rocks/donations

21 Feb 20061h 8min

Populært innen Teknologi

smart-forklart
romkapsel
rss-avskiltet
teknisk-sett
tomprat-med-gunnar-tjomlid
kunstig-intelligens-med-morten-goodwin
rss-impressions-2
nasjonal-sikkerhetsmyndighet-nsm
shifter
energi-og-klima
teknologi-og-mennesker
fotopodden
rss-for-alarmen-gar
i-loopen
rss-snakk-om-sikkerhet
rss-var-alt-bedre-for
fornybaren
rss-digitaliseringspadden
rss-30-minutter-inn-i-fremtiden
rss-tendencast-kunstig-intelligens-og-juss