Causal Bandits Podcast
MSFT Scientist: Agents, Causal AI & Future of DoWhy | Amit Sharma S2E4 | CausalBanditsPodcast.com
Apr 14, 2025
Amit Sharma, Principal Researcher at Microsoft Research and co-creator of the DoWhy library, discusses the future of agentic systems and their impact on complex human tasks. He highlights the challenges in current frameworks, particularly around verification, while emphasizing innovative approaches in causal modeling. The conversation touches on integrating large language models to improve decision-making and the creation of the Duy library for causal inference, aiming to enhance accessibility for newcomers in the field. This engaging dialogue showcases the intersection of causality and AI in shaping robust systems.
01:10:56
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Agentic systems are nearing full automation, yet their foundational technology requires further validation for practical applications.
- Causal reasoning enhances agents' decision-making by enabling them to learn from diverse environments, improving their real-world effectiveness.
Deep dives
The Rising Importance of Causality in Agent Interactions
Causality is becoming critical as agents start to interact in the real and online worlds. The speaker highlights that agents must optimize their actions and rewards, emphasizing the need to determine which behaviors to incentivize or penalize. This questioning encompasses not only which agents contribute positively but also involves concepts of blame for underperforming agents. As these interactions grow, the introduction of causal frameworks may facilitate a deeper understanding of agents' real-world effectiveness.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
