Go offline with the Player FM app!
How Salesforce are using LLMs with Greg Bennett
Manage episode 373988862 series 2093893
Greg Bennett’s the final Conversations2 interviewee focused on large language models!
When I heard that Salesforce have adopted LLMs at scale (and also heard that they had started to design and build this prior to ChatGPT’s release) I wanted to know more!
I’ve known Greg for years and have always found him to be warm, knowledgeable and an expert at making complex subjects understandable. He didn’t disappoint here - we spoke about thinking in systems and how that relates to conversational AI, how LLMs affect conversation design (and how conversation designers are key to the best usage of LLMs), how his team of designers work with the wider team, and Salesforce’s recent push into Generative Conversational AI.
So listen up to Greg’s thoughts on the best ways to use LLMs in conversational AI! Salesforce have gone all-in on generative conversational AI and Greg’s team have made that possible.
00:00Start
00:29Greg's introduction
03:55What's your favourite bot?
05:11What's the most useful thing you use at work?
06:21Which conversation designer should we all know about?
08:15Conversations are systematic, and design should be too
10:17What does 'generative conversational AI' mean to you?
11:38How have you been incoporating generative conversational AI into your work at Salesforce?
16:05We need expertise when writing prompts for LLMs
17:45How does your team collaborate with the wider Salesforce team?
20:50What benefits did you envision and how close are you now?
24:23How has this affected the day to day work of conversation designers?
27:46Now we need to be able to educate people about how to do conversational AI well
29:52We're thinking conceptually about language
32:43Is this a new phase of conversation design?
36:32How do you minimise the risks?
39:49Do you continue to iterate together with engineering?
41:37The model has a risk of learning from bad behaviour
42:46How do you stay up to date with generative AI?
44:05Researching attempts to break LLMs on social media gives great REAL data
45:49When will you next speak live?
46:46Outro
Hosted on Acast. See acast.com/privacy for more information.
317 episodes
Manage episode 373988862 series 2093893
Greg Bennett’s the final Conversations2 interviewee focused on large language models!
When I heard that Salesforce have adopted LLMs at scale (and also heard that they had started to design and build this prior to ChatGPT’s release) I wanted to know more!
I’ve known Greg for years and have always found him to be warm, knowledgeable and an expert at making complex subjects understandable. He didn’t disappoint here - we spoke about thinking in systems and how that relates to conversational AI, how LLMs affect conversation design (and how conversation designers are key to the best usage of LLMs), how his team of designers work with the wider team, and Salesforce’s recent push into Generative Conversational AI.
So listen up to Greg’s thoughts on the best ways to use LLMs in conversational AI! Salesforce have gone all-in on generative conversational AI and Greg’s team have made that possible.
00:00Start
00:29Greg's introduction
03:55What's your favourite bot?
05:11What's the most useful thing you use at work?
06:21Which conversation designer should we all know about?
08:15Conversations are systematic, and design should be too
10:17What does 'generative conversational AI' mean to you?
11:38How have you been incoporating generative conversational AI into your work at Salesforce?
16:05We need expertise when writing prompts for LLMs
17:45How does your team collaborate with the wider Salesforce team?
20:50What benefits did you envision and how close are you now?
24:23How has this affected the day to day work of conversation designers?
27:46Now we need to be able to educate people about how to do conversational AI well
29:52We're thinking conceptually about language
32:43Is this a new phase of conversation design?
36:32How do you minimise the risks?
39:49Do you continue to iterate together with engineering?
41:37The model has a risk of learning from bad behaviour
42:46How do you stay up to date with generative AI?
44:05Researching attempts to break LLMs on social media gives great REAL data
45:49When will you next speak live?
46:46Outro
Hosted on Acast. See acast.com/privacy for more information.
317 episodes
All episodes
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.