Welcome to the Pieces AI productivity podcast, where we dig into how experts use AI to be more productive, as well as geeking out in general on different AI topics.
🤖 In todays episode, Jim is joined by David Packman, the co-founder of Packabby robotics, a company that makes social companion robots powered by AI. Jim and David reminisce on Clippy (it looks like you’re writing a letter), and talk about how AI in particular in cute robots provides a much needed social interaction for people on the spectrum who need a way to practise socializing, or for anyone who wants to talk through something with someone who won’t judge.
David also talks about the power of social robots with long-term memory, and how enabling what appears to be simple memories, such as remembering what changes you make to a recipe, can unlock a whole new powerful capability in your robot, just like how the Pieces Long-Term Memory enables a new style of AI prompts to retrieve relevant information for you about your activities.
🌐 Links:
Packabby Robotics
Connect with David on LinkedIn
Mini Moe on Indiegogo
Build a 3D Printed Clippy
Instructions to build Clippy
👉 Try Pieces for free: https://pieces.app
💡 Learn more about Pieces features: https://pieces.app/features
Connect with Pieces:
X: https://x.com/getpieces
Bluesky: https://bsky.app/profile/getpieces.bsky.social
LinkedIn: https://www.linkedin.com/company/getpieces/
Instagram: https://www.instagram.com/getpieces/
Discord: https://pieces.app/discord
In this episode:
0:00:00 - Intro
0:01:49 - Why and how David built Clippy
0:08:49 - Introducing Mini Moe, a small robot companion
0:14:18 - Why humans like interacting with anthropomorphic characters
0:24:33 - Using decision trees to handle difficult questions
0:32:05 - Whiskas, the cooking robot
0:36:42 - Long-Term memory is important for social robots
0:42:59 - Get you brown Mini Moe
0:46:29 - More on conversational and long-term memory
Information
- Show
- FrequencyUpdated Weekly
- PublishedMarch 25, 2025 at 3:00 PM UTC
- Length54 min
- Episode6
- RatingClean
