Peter has written and shared a lot about Large Language Models in recent posts and blogs. We wanted to get his perspective on various things, especially now that Voiceflow have incorporated LLMs into their tool. 

How can conversation designers use LLMs now? How does Peter use the LLM as a sounding board to help him craft prompts? Where might we be using them next? How can we document dynamic conversational designs (when LLMs can allow conversations to go off-rails)?

Ben asked him these questions and more…

0:00:00Start

0:02:44About Peter

0:05:44What's your favourite bot?

0:06:57What Aussie lingo should bots know?

0:09:36Pick 3 words to describe your career so far?

0:12:03Do you draw on your former jobs for inspiration?

0:14:06What's it like being the first Conversation Design Advocate at VoiceFlow?

0:18:12What's the best way to incorporate VoiceFlow into a workflow?

0:21:24Are you seeing more interest in conversation design now?

0:23:18Where do you see LLMs being used now?

0:28:52Could conversation designers become an organisation's knowledge experts?

0:31:15We're all making our first steps with LLMs

0:33:43It's easy to fall under the spell of an LLM and think it knows everything

0:35:36Has conversation design changed forever now?

0:37:08Are we over-excited or being too timid?

0:40:08Now we can design conversations that are far more dynamic

0:41:54Are there best practices for documenting designs with LLMs?

0:44:10How does Peter use an LLM to help write the prompt?

0:46:42Have you found ways to avoid 'hallucinations'?

0:49:56How would a conversational system work without an NLU?

0:53:32Are we about to see a new use case for LLMs?

0:57:55How will this affect the work of conversation designers in the next 15 years?

1:03:12Why's there not been more shocking news about misuse of LLMs?

1:05:39We need to constantly monitor where this tech is going

1:06:52Outro

Hosted on Acast. See acast.com/privacy for more information.