Gradient Descent - Podcast about AI and Data

Latest episodes

• A History of NLP and Wisecube’s AI Journey

  June 3, 2025 · 38 min

  In this episode, Vishnu and Alex reflect on Wisecube’s 8-year journey and over 15 years of experience in AI and NLP. They discuss pioneering search engines using TF-IDF to build knowledge graphs (Orpheus), addressing LLM reliability with…

• LLM Fine-Tuning: RLHF vs DPO and Beyond

  May 13, 2025 · 38 min

  In this episode of Gradient Descent, we explore two competing approaches to fine-tuning LLMs: Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO). Dive into the mechanics of RLHF, its computational…

• The Future of Prompt Engineering: Prompts to Programs

  April 29, 2025 · 36 min

  Explore the evolution of prompt engineering in this episode of Gradient Descent. Manual prompt tuning — slow, brittle, and hard to scale — is giving way to DSPy, a framework that turns LLM prompting into a structured, programmable, and…

• Agentic AI – Hype or the Next Step in AI Evolution?

  April 12, 2025 · 41 min

  Let’s dive into Agentic AI, guided by the "Cognitive Architectures for Language Agents" (CoALA) paper. What defines an agentic system? How does it plan, leverage memory, and execute tasks? We explore semantic, episodic, and procedural…

• LLM as a Judge: Can AI Evaluate Itself?

  March 22, 2025 · 32 min

  In the second episode of Gradient Descent, Vishnu Vettrivel (CTO of Wisecube) and Alex Thomas (Principal Data Scientist) explore the innovative yet controversial idea of using LLMs to judge and evaluate other AI systems. They discuss the…

Full episode archive on Apple Podcasts →