Matt Taylor is back on VUX world as he shares LLMs in practice.
Presented by Tidio
Grow your online store with the #1 customer success tool for eCommerce. Engage with your customers and website visitors in real-time. Provide personalized product recommendations. Use AI-powered chatbot workflows to move prospects through your sales funnel. And so much more.
Save 20% on your subscription with the promo code VUX.
Find out more about Tidio (use the link https://www.tidio.com/partners/vux/)
Are we coming to the end of the hype cycle with Large Language Models? Are we finally finding where they fit best in enterprise automation? Are are we still rolling through the hype? Matt Taylor, Co-Founder and CPO, Knowbl, joins us to shine a light
In this episode
00:00 Introduction
03:54 Welcome Matt
10:40 The risk of incorrect / dangerous information with chatbots
14:01 Are customers trying to break LLMs?
18:20 Technology advancements
22:33 Size of models
25:18 Fine tuning of models
29:14 Transactional experiences
33:00 How good are LLMs?
37:00 Do certain models perform better?
40:05 Where we are with technology today
43:40 Inflated expectations
48:37 Sorting information before using an LLM
52:30 Will people see unintended bias in LLMs?
55:58 Multi neurone direction
58:58 Obstacles coming up
1:01:01 Biggest misconception around large language models
1:03:20 Short term predictions
1:08:23 Outro
