{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/5a8145b3ac34577e1adf2624/64b929ace0e718001121d19d?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Talking LLMs with Voiceflow’s first Senior Conversation Design Advocate - Peter Isaacs!","thumbnail_width":200,"thumbnail_height":200,"thumbnail_url":"https://open-images.acast.com/shows/5a8145b3ac34577e1adf2624/1689856251677-df236b8e09062810418dcff60ef931ad.jpeg?height=200","description":"<p>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.&nbsp;</p><p><br></p><p>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)?</p><p><br></p><p>Ben asked him these questions and more…</p><p><br></p><p>0:00:00\tStart</p><p>0:02:44\tAbout Peter</p><p>0:05:44\tWhat's your favourite bot?</p><p>0:06:57\tWhat Aussie lingo should bots know?</p><p>0:09:36\tPick 3 words to describe your career so far?</p><p>0:12:03\tDo you draw on your former jobs for inspiration?</p><p>0:14:06\tWhat's it like being the first Conversation Design Advocate at VoiceFlow?</p><p>0:18:12\tWhat's the best way to incorporate VoiceFlow into a workflow?</p><p>0:21:24\tAre you seeing more interest in conversation design now?</p><p>0:23:18\tWhere do you see LLMs being used now?</p><p>0:28:52\tCould conversation designers become an organisation's knowledge experts?</p><p>0:31:15\tWe're all making our first steps with LLMs</p><p>0:33:43\tIt's easy to fall under the spell of an LLM and think it knows everything</p><p>0:35:36\tHas conversation design changed forever now?</p><p>0:37:08\tAre we over-excited or being too timid?</p><p>0:40:08\tNow we can design conversations that are far more dynamic</p><p>0:41:54\tAre there best practices for documenting designs with LLMs?</p><p>0:44:10\tHow does Peter use an LLM to help write the prompt?</p><p>0:46:42\tHave you found ways to avoid 'hallucinations'?</p><p>0:49:56\tHow would a conversational system work without an NLU?</p><p>0:53:32\tAre we about to see a new use case for LLMs?</p><p>0:57:55\tHow will this affect the work of conversation designers in the next 15 years?</p><p>1:03:12\tWhy's there not been more shocking news about misuse of LLMs?</p><p>1:05:39\tWe need to constantly monitor where this tech is going</p><p>1:06:52\tOutro</p><p><br></p><p><br></p>","author_name":"Kane Simms"}