From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

Author: Sam Charrington May 14, 2025 Duration: 1:01:25
Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mahesh highlights the crucial role of data curation, evaluation, and error analysis in model performance, and explains why RL offers a more robust alternative to prompting, and how it can improve multi-step tool use capabilities. We also explore the limitations of supervised fine-tuning (SFT) for tool-augmented reasoning tasks, the reward-shaping strategies they’ve used, and Bespoke Labs’ open-source libraries like Curator. We also touch on the models MiniCheck for hallucination detection and MiniChart for chart-based QA. The complete show notes for this episode can be found at https://twimlai.com/go/731.

Hosted by industry analyst and commentator Sam Charrington, The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) serves as a vital conduit between cutting-edge research and its real-world implications. This isn't just a series of technical lectures; it's a series of conversations that unpack how AI and machine learning are actively reshaping industries and societal structures. Each episode connects you directly with leading researchers, engineers, and innovative thinkers who are defining the frontiers of the field. The discussions go beyond abstract theory to explore the practical challenges, ethical considerations, and business transformations driven by these technologies. Whether you're a data scientist deep in the code, a tech-savvy leader strategizing implementation, or simply fascinated by the future of intelligent systems, this podcast provides the context and depth needed to stay informed. By focusing on the people behind the algorithms and the ideas powering the platforms, Sam creates a resource that is both intellectually substantive and genuinely engaging, building a thoughtful community around one of the most significant technological shifts of our time.
Author: Language: English Episodes: 50

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Podcast Episodes
From Voice Agents to AI Avatars with Alexander Smola - #777 [not-audio_url] [/not-audio_url]

Duration: 1:04:58
Voice AI has gotten remarkably good, but natural conversation remains a high bar. Small delays, awkward interruptions, or the wrong tone can quickly break the illusion—and adding vision and visual presence only raises th…
World Models and the Future of Spatial AI with Justin Johnson - #775 [not-audio_url] [/not-audio_url]

Duration: 1:06:02
In this episode, Justin Johnson, co-founder of World Labs, joins us to discuss world models and the emerging field of spatial AI. We explore why many researchers see capabilities beyond language as an important frontier…
Why Models Are AI’s Next Training Dataset with Damian Borth - #772 [not-audio_url] [/not-audio_url]

Duration: 47:00
For more than a decade, AI has advanced by training ever-larger models on ever-larger datasets. But as high-quality training data becomes harder to find and pretraining grows increasingly expensive, researchers are looki…
How AI Learns to Smell with Alex Wiltschko - #771 [not-audio_url] [/not-audio_url]

Duration: 59:55
In this episode, Alex Wiltschko, founder and CEO of Osmo, joins the show to discuss his goal of giving computers a sense of smell and what it takes to build olfactory intelligence. We explore the science behind smell, fr…