Intro

This chapter explores the complexities of continuous learning in AI, focusing on reinforcement fine-tuning and its influence on model training. The conversation addresses the transition from static to dynamic models and the associated challenges, such as reward hacking and the management of specialized AIs.

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

This crossover episode from Inference by Turing Post features CEO Dev Rishi of Predibase discussing the shift from static to continuously learning AI systems that can adapt and improve from ongoing user feedback in production. Rishi provides grounded insights from deploying these dynamic models to real enterprise customers in healthcare and finance, exploring both the massive potential upside and significant safety challenges of reinforcement learning at scale. The conversation examines how "practical specialized intelligence" could reshape the AI landscape by filling economic niches efficiently, potentially offering a more stable alternative to AGI development. This discussion bridges theoretical concepts with real-world deployment experience, offering a practical preview of AI systems that "train once and learn forever."

Turing Post channel: @RealTuringPost Turpin Post website: https://www.turingpost.com

Sponsors:

Google Gemini 2.5 Flash :

Build faster, smarter apps with customizable reasoning controls that let you optimize for speed and cost. Start building at https://aistudio.google.com

Labelbox:

Labelbox pairs automation, expert judgment, and reinforcement learning to deliver high-quality training data for cutting-edge AI. Put its data factory to work for you, visit https://labelbox.com

Oracle Cloud Infrastructure:

Oracle Cloud Infrastructure (OCI) is the next-generation cloud that delivers better performance, faster speeds, and significantly lower costs, including up to 50% less for compute, 70% for storage, and 80% for networking. Run any workload, from infrastructure to AI, in a high-availability environment and try OCI for free with zero commitment at https://oracle.com/cognitive

The AGNTCY:

The AGNTCY is an open-source collective dedicated to building the Internet of Agents, enabling AI agents to communicate and collaborate seamlessly across frameworks. Join a community of engineers focused on high-quality multi-agent software and support the initiative at https://agntcy.org

NetSuite by Oracle:

NetSuite by Oracle is the AI-powered business management suite trusted by over 42,000 businesses, offering a unified platform for accounting, financial management, inventory, and HR. Gain total visibility and control to make quick decisions and automate everyday tasks—download the free ebook, Navigating Global Trade: Three Insights for Leaders, at https://netsuite.com/cognitive

PRODUCED BY:

https://aipodcast.ing

CHAPTERS:

(00:00) Sponsor: Google Gemini 2.5 Flash

(00:31) About the Episode

(03:46) Training Models Continuously

(05:03) Reinforcement Fine-Tuning Revolution

(09:31) Agentic Workflows Challenges (Part 1)

(12:51) Sponsors: Labelbox | Oracle Cloud Infrastructure

(15:28) Agentic Workflows Challenges (Part 2)

(15:41) ChatGPT Pivot Moment

(19:59) Planning AI Future