Gradient Descent - Podcast about AI and Data

“Gradient Descent" is a podcast that delves into the depths of artificial intelligence and data science. Hosted by Vishnu Vettrivel (Founder of Wisecube AI) and Alex Thomas (Principal Data Scientist), the show explores the latest trends, innovations, and practical applications in AI and data science. Join us to learn more about how these technologies are shaping our future.

Last refreshed: July 23rd, 2025 at 7:40 AM ⓘ

Follow this podcast in the Metacast mobile app to refresh it and see new episodes.

Follow on

Apple Podcasts

Spotify

RSS

Podcasts are better in Metacast mobile app

Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more

Episodes

A History of NLP and Wisecube’s AI Journey

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 Pythia, exploring key milestones in AI development, and the evolution of NLP. Topics include the Eliza effect, real-world healthcare and research applications, CAC, drug discovery, and Wisecube's recent acquisition by John Snow Labs. They explore the future of N...

Jun 03, 2025•38 min•Season 1Ep. 6

LLM Fine-Tuning: RLHF vs DPO and Beyond

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 challenges, and how DPO simplifies the process by eliminating the need for a separate reward model. We also discuss supervised fine-tuning, emerging methods like Identity Preference Optimization (IPO) and Kahneman-Tversky Optimization (KTO), and their real-world ...

May 13, 2025•38 min•Season 1Ep. 5

The Future of Prompt Engineering: Prompts to Programs

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 optimizable process. Learn how DSPy’s modular approach — with Signatures, Modules, and Optimizers — enables LLMs to tackle complex tasks like multi-hop reasoning and math problem solving, achieving accuracy comparable to much larger models. We also dive into real-...

Apr 29, 2025•36 min•Season 1Ep. 4

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

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 memory, discuss decision-making loops, and examine how agents integrate with external APIs (think LangGraph). Learn how AI tackles complex automation — from code generation to playing Minecraft — and why designing robust action spaces is key to scaling systems. We ...

Apr 12, 2025•41 min•Season 1Ep. 3

LLM as a Judge: Can AI Evaluate Itself?

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 hidden human role in AI training, limitations of traditional benchmarks, automated evaluation strengths and weaknesses, and best practices for building reliable AI judgment systems. Timestamps: 00:00 – Introduction & Context 01:00 – The Role of Humans in AI ...

Mar 22, 2025•32 min•Season 1Ep. 2

AI Scaling Laws, DeepSeek’s Cost Efficiency & The Future of AI Training

In this first episode of Gradient Descent, hosts Vishnu Vettrivel (CTO of Wisecube AI) and Alex Thomas (Principal Data Scientist) discuss the rapid evolution of AI, the breakthroughs in LLMs, and the role of Natural Language Processing in shaping the future of artificial intelligence. They also share their experiences in AI development and explain why this podcast differs from other AI discussions. Chapters: 00:00 – Introduction 01:56 – DeepSeek Overview 02:55 – Scaling Laws and Model Performanc...

Mar 06, 2025•40 min•Season 1Ep. 1

Hosted on Spotify for Creators (Anchor)

For the best experience, listen in Metacast app for iOS or Android