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)

David Aiken on Azure

David Aiken on Azure

David Aiken is back, this time to lay down the skinny on Azure. What can you do with it? What doesn't it do? All this and more! Now how much would you pay???Support this podcast at — https://redcircle.com/net-rocks/donations

16 Dec 200853min

Catching up with Oren Eini

Catching up with Oren Eini

Oren Eini spoke to Carl and Richard at 0redev in Malmo, Sweden in November about the latest version of Rhino Mocks, Oren's mocking framework. Oren also talks about mocking in General.Support this podcast at — https://redcircle.com/net-rocks/donations

12 Dec 200858min

Oslo is Love with Chris Sells

Oslo is Love with Chris Sells

Chris Sells is here to explain Oslo for real. Don and Doug couldn't really dig deep into Oslo before the PDC, but now that it has been announced, Chris is here to splain it to everyone in clear English.Support this podcast at — https://redcircle.com/net-rocks/donations

10 Dec 20081h 2min

Show 400!

Show 400!

Carl and Richard look back on the last year joined by a cast of former guests and conference speakers in the hotel bar at the Marriott Chateau Champlain in Montreal while at DevTeach. WARNING: Unbleeped F-Bombs!Support this podcast at — https://redcircle.com/net-rocks/donations

5 Dec 200855min

The HP TouchSmart!

The HP TouchSmart!

Carl and Richard talk to Irwin Kwan, PM on TouchSmart team at Hewlett-Packard; Oluf Nissen, Dev on the TouchSmart team; Muffi Ghadiali, marketing for HP Touchsmart Software; and Matt Whitlock from Capable Networks, developer of www.touchsmartcommunity.com, a site dedicated to the TouchSmart community. HP has just released a set of development guidelines for the TouchSmart. Check it out!Support this podcast at — https://redcircle.com/net-rocks/donations

2 Dec 200844min

Glenn Block on MEF

Glenn Block on MEF

Glenn Block talk to Carl and Richard about Microsoft MEF (Managed Extensibility Framework), which provides scalable extensibility for any application.Support this podcast at — https://redcircle.com/net-rocks/donations

27 Nov 200846min

Michael Feathers talks Legacy Code

Michael Feathers talks Legacy Code

Carl and Richard talk to Michael Feathers about how to bring legacy code (that which has no testing code coverage) into the 21st century.Support this podcast at — https://redcircle.com/net-rocks/donations

25 Nov 200859min

The Future of Web Development Panel

The Future of Web Development Panel

Recorded live at Devreach in Sofia, Bulgaria, this is a discussion with Miguel Castro, Todd Anglin, Shawn Wildermuth, and Steven Smith. Mark Dunn filled in for Richard.Support this podcast at — https://redcircle.com/net-rocks/donations

20 Nov 20081h 14min

Populärt inom Teknik

uppgang-och-fall
rss-racevecka
elbilsveckan
market-makers
svd-tech-brief
natets-morka-sida
rss-uppgang-och-fall
skogsforum-podcast
har-vi-akt-till-mars-an
solcellskollens-podcast
developers-mer-an-bara-kod
rss-elektrikerpodden
bli-saker-podden
bilar-med-sladd
rss-technokratin
rss-en-ai-till-kaffet
lordag-med-m3
rss-badfluence
rss-sakerhetspodcasten
rss-veckans-ai