Super Data Science: ML & AI Podcast with Jon Krohn 809: Agentic AI, with Shingai Manjengwa
Aug 13, 2024
Shingai Manjengwa, a representative from ChainML, dives into the transformative realm of Agentic AI. He showcases how these AI agents are streamlining tasks like travel bookings and offering daily inspiration. Shingai discusses the innovative Theoriq protocol and how blockchain technology fosters trust in AI systems. He also highlights the potential of multi-agent systems to tackle complex challenges, and shares insights on the emerging Council Analytics tool that allows users to interact with data in natural language.
AI Snips
Chapters
Transcript
Episode notes
AI Agents Defined
- AI agents are software leveraging AI, particularly LLMs, to automate tasks.
- They specialize in specific areas like travel planning, creating a seamless user experience.
Theoric Protocol and Trust
- Theoric, ChainML's protocol, assists in agent selection by providing metadata on a distributed ledger.
- This solves AI's trust problem by allowing users to see agent origins and functionality.
LLM Error Anecdote
- Shingai Manjengwa asked an LLM for an image of Zimbabwe from space, but it pointed to Madagascar.
- This highlights the difficulty of holding service providers accountable for LLM errors.