GenAI Level UP
Episodes
Master the New Physics of AI with Context Graphs & GraphRAG
01 Feb 2026
Contributed by Lukas
Stop trying to find the "magic words" to hack your LLM. The era of the Prompt Engineer—tweaking adjectives and hoping for the best—is of...
Context Graph
25 Jan 2026
Contributed by Lukas
Stop feeding your AI static facts in a dynamic world.Most RAG systems and Knowledge Graphs rely on a fundamental unit called the "Triple" (S...
Nested Learning: The Illusion of Deep Learning Architectures
14 Nov 2025
Contributed by Lukas
Why do today's most powerful Large Language Models feel... frozen in time? Despite their vast knowledge, they suffer from a fundamental flaw: a fo...
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
01 Nov 2025
Contributed by Lukas
What if you could build AI agents that get smarter with every task, learning from successes and failures in real-time—without the astronomical cost ...
MemGPT: Towards LLMs as Operating Systems
01 Nov 2025
Contributed by Lukas
Have you ever felt the frustration of an LLM losing the plot mid-conversation, its brilliant insights vanishing like a dream? This "goldfish memo...
DeepSeek-OCR: Contexts Optical Compression
24 Oct 2025
Contributed by Lukas
The single biggest bottleneck for Large Language Models isn't intelligence—it's cost. The quadratic scaling of self-attention makes processi...
A Definition of AGI
23 Oct 2025
Contributed by Lukas
For decades, Artificial General Intelligence has been a moving target, a nebulous concept that shifts every time a new AI masters a complex task. This...
Teaching LLMs to Plan: Logical CoT Instruction Tuning for Symbolic Planning
05 Oct 2025
Contributed by Lukas
Large Language Models (LLMs) like GPT and LLaMA have shown remarkable general capabilities, yet they consistently hit a critical wall when faced with ...
Five Orders of Magnitude: Analog Gain Cells Slash Energy and Latency for Ultra-Fast LLMs
05 Oct 2025
Contributed by Lukas
In this episode, we explore an innovative approach to overcoming the notorious energy and latency bottlenecks plaguing modern Large Language Models (L...
The Great Undertraining: How a 70B Model Called Chinchilla Exposed the AI Industry's Billion-Dollar Mistake
03 Aug 2025
Contributed by Lukas
For years, a simple mantra has cost the AI industry billions: bigger is always better. The race to scale models to hundreds of billions of parameters—...
RewardAnything: Generalizable Principle-Following Reward Models
03 Aug 2025
Contributed by Lukas
What if the biggest barrier to truly aligned AI wasn't a lack of data, but a failure of language? We spend millions on retraining LLMs for every n...
AI That Evolves: Inside the Darwin Gödel Machine
30 Jun 2025
Contributed by Lukas
What if an AI could do more than just learn from data? What if it could fundamentally improve its own intelligence, rewriting its source code to becom...
The AI Reasoning Illusion: Why 'Thinking' Models Break Down
14 Jun 2025
Contributed by Lukas
The latest AI models promise a revolutionary leap: the ability to "think" through complex problems step-by-step. But is this genuine reasoning, or an ...
When AI Rewrites Its Own Code to Win: Agent of Change
13 Jun 2025
Contributed by Lukas
Large Language Models have a notorious blind spot: long-term strategic planning. They can write a brilliant sentence, but can they execute a brilliant...
Eureka: How AI Learned to Write Better Reward Functions Than Human Experts
07 Jun 2025
Contributed by Lukas
Reward engineering is one of the most brutal, time-consuming challenges in AI—a "black art" that forms the very foundation of how intellig...
AlphaEvolve: How Google's AI Now Evolves Code to Solve Decades-Old Puzzles & Optimize Our World
04 Jun 2025
Contributed by Lukas
Imagine an AI that doesn't just write code, but evolves it—learning, adapting, and iteratively improving to conquer challenges that have stumped...
LLM Evaluation - How We Really Know If AI Is Getting Smarter
19 May 2025
Contributed by Lukas
AI leaps forward every week, but how do we cut through the noise and truly measure progress? This isn't just academic; it's fundamental to trusting an...
RAG-MCP: Mitigating Prompt Bloat and Enhancing Tool Selection for LLM
13 May 2025
Contributed by Lukas
Large Language Models (LLMs) face significant challenges in effectively using a growing number of external tools, such as those defined by the Model C...
DeepSeek Prover V2 - AI's New Frontier in Formal Mathematics
12 May 2025
Contributed by Lukas
In this episode, we dissect DeepSeek Prover V2, an open-source large language model pushing the boundaries of AI in formal theorem proving using Lean ...
From QA to AI Improvement Engineer: Navigating the Shift in the AI Era
05 May 2025
Contributed by Lukas
Quality Engineering (QE) professionals are well-positioned to transition into AI Improvement Engineering roles due to their deep knowledge of testin...
Defeating Prompt Injections by Design: The CaMeL Approach
03 May 2025
Contributed by Lukas
This episode delves into CaMeL, a novel defense mechanism designed to combat prompt injection attacks in Large Language Model (LLM) agents. Inspired b...
The Blueprint Behind Google—and the Future of AI Retrieval
28 Apr 2025
Contributed by Lukas
In this episode, we unearth the untold story of how Google engineered one of the most powerful information retrieval systems in history—and why its ...
Running Down a Dream: Bill Gurley’s Roadmap to a Career You Love
20 Apr 2025
Contributed by Lukas
[Level Up With Gen AI Series] We believe in harnessing the power of AI to unlock human potential.We unpack Bill Gurley’s legendary talk “Running D...
The Divine Discontent (Constructive Dissatisfaction): Inside Ogilvy's Creative Habits
20 Apr 2025
Contributed by Lukas
[Level Up With Gen AI Series] We believe in harnessing the power of AI to unlock human potential.Are you ready to take your creativity to the next lev...
Don’t Just Generate, Dominate: Your Generative AI Level Up Starts Now
19 Apr 2025
Contributed by Lukas
Are you content with merely functional AI? David Ogilvy wouldn't be. This podcast embodies his spirit of "divine discontent", pushing be...
How AI Learned to Chat About Pictures: Inside the MoshiVis Model
02 Apr 2025
Contributed by Lukas
How do you teach a sophisticated speech AI to understand and discuss images, especially when paired image-speech data is rare? This episode unpacks Mo...
DeepSeek LLM: The Open Source AI Revolution
24 Jan 2025
Contributed by Lukas
Dive into the groundbreaking world of DeepSeek LLM, an open-source language model that's challenging the dominance of closed-source AI. This epis...
Titans: Learning to Memorize at Test Time
18 Jan 2025
Contributed by Lukas
Are current AI models hitting a memory wall? Join us as we delve into the fascinating research behind "Titans: Learning to Memorize at Test Time,...
Memory Layers at Scale: Revolutionizing AI Efficiency and Factuality
03 Jan 2025
Contributed by Lukas
Join us for an in-depth exploration of the groundbreaking research paper, "Memory Layers at Scale." Discover how trainable key-value lookup mechanisms...
LOCOMO: Unlocking Long-Term Memory in Conversational AI
31 Dec 2024
Contributed by Lukas
How well can AI remember and use information in long conversations? This episode explores the groundbreaking LOCOMO dataset, a unique resource design...
Beyond the Short Chat: Exploring Long-Term Memory in AI
30 Dec 2024
Contributed by Lukas
Ready for a deep dive into the fascinating world of large language models? In this episode, we push AI chatbots to their conversational limits—span...
Generative AI: Ethical Considerations, Future Trends, and a Path for Continued Learning - Level 10
20 Dec 2024
Contributed by Lukas
This final episode wraps up our journey into the world of generative AI, providing a crucial overview of the ethical and societal considerations, and ...
Beyond GPT-4V and Sora: Multi-Modal Generative AI - Level 9
20 Dec 2024
Contributed by Lukas
This podcast offers a comprehensive exploration of multi-modal generative AI. We examine the two dominant families of techniques, the multi-modal larg...
From Noise to Creation: Diffusion Models - Level 8
19 Dec 2024
Contributed by Lukas
Explore the revolutionary world of diffusion models, a cutting-edge AI technology that learns to reverse the process of turning data into noise to ge...
Learning with BERT and GPT-3: Bridging the Human-AI Gap - Level 7
18 Dec 2024
Contributed by Lukas
Join us on a fascinating journey into the world of natural language processing, where we explore groundbreaking advancements in AI learning. From BERT...
Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) - Level 5
15 Dec 2024
Contributed by Lukas
This episode delves into the groundbreaking RNN Encoder-Decoder architecture, a neural network model that revolutionized machine translation. We'll e...
GANs Unpacked: Exploring the Magic Behind Generative Adversarial Networks - Level 4
12 Dec 2024
Contributed by Lukas
Inspired by Ian Goodfellow's seminal paper, we explore the core principles of Generative Adversarial Networks (GANs), where creativity meets competiti...
How AI Learns to Imagine: The Magic of Variational Autoencoders (VAE) - Level 3
09 Dec 2024
Contributed by Lukas
Variational Autoencoders (VAEs) are a fascinating type of deep learning model that combines neural networks with probabilistic modeling. This podcast...
Unveiling the World of Deep Generative Models: Insights and Challenges - Level 2
07 Dec 2024
Contributed by Lukas
Dive into the fascinating universe of Deep Generative Models (DGMs) with this insightful podcast. Explore how these advanced neural networks simulate...
Teaching Machines to Learn: Inside the Training of Neural Networks - Level 1
06 Dec 2024
Contributed by Lukas
We break down how neural networks learn from data, starting with forward and backward passes, loss functions, and optimization methods like gradient d...
Demystifying ANNs: The Brain-Inspired Marvel of AI - Level 1
05 Dec 2024
Contributed by Lukas
Dive into the fascinating world of Artificial Neural Networks (ANNs) in this episode, where we explore their structure, function, and real-world appli...
Deep Learning Fundamentals - Level 1
01 Dec 2024
Contributed by Lukas
Join us as we explore the fascinating world of Deep Learning! This podcast will break down complex concepts into digestible pieces, covering everythin...
Generative Agent Simulations of 1,000 People
27 Nov 2024
Contributed by Lukas
Imagine a world where scientists can simulate human behavior with incredible accuracy. Researchers at Stanford University have developed a new tool ca...
Attention Is All You Need - Level 6
27 Nov 2024
Contributed by Lukas
The Transformer: Revolutionizing Sequence Transduction with Self-Attention This episode explores the groundbreaking Transformer, a novel neural netwo...