GenAI Level UP

Imagine holding a wrench on an assembly line. Suddenly, it leaps from your hand, sprouts its own mechanical arms, and begins forging a faster, lighter wrench without you. You are no longer the creator; you are a bystander. This isn't a science fiction thought experiment. According to internal data from Anthropic, it is the active, everyday reality unfolding inside the world's most advanced...

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 officially over. We are entering the age of the Context Engineer , a discipline not about "cooking the meal," but about "stocking the pantry" with architected, structured intelligence. In this episode of GenAI Level UP , we dismantle th...

Stop feeding your AI static facts in a dynamic world. Most RAG systems and Knowledge Graphs rely on a fundamental unit called the "Triple" (Subject, Verb, Object). It’s efficient, but it’s brittle. It tells you Steve Jobs is the Chairman of Apple, but fails to tell you when . It tells you where a diplomat works, but assumes that’s where they hold citizenship. This lack of nuance is the r...

Why do today's most powerful Large Language Models feel... frozen in time? Despite their vast knowledge, they suffer from a fundamental flaw: a form of digital amnesia that prevents them from truly learning after deployment. We’ve hit a wall where simply stacking more layers isn't the answer. This episode unpacks a radical new paradigm from Google Research called " Nested Learning, &q...

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 and complexity of constant fine-tuning? This isn't a distant dream; it's a new paradigm that could fundamentally change how we develop intelligent systems. The current approach to AI adaptation is broken. We're trapped between rigid, hard-c...

Have you ever felt the frustration of an LLM losing the plot mid-conversation, its brilliant insights vanishing like a dream? This "goldfish memory"—the limited context window—is the Achilles' heel of modern AI, a fundamental barrier we've been told can only be solved with brute-force computation and astronomically expensive, larger models. But what if that's the wrong way to...

The single biggest bottleneck for Large Language Models isn't intelligence—it's cost. The quadratic scaling of self-attention makes processing truly long documents prohibitively expensive, a fundamental barrier that has stalled progress. But what if the solution wasn't more compute, but a radically simpler, more elegant idea? In this episode, we dissect a groundbreaking paper from Deep...

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 ambiguity fuels unproductive debates and obscures the real gap between today's specialized models and true human-level cognition. This episode changes everything. We unpack a groundbreaking, quantifiable framework that finally stops the goalpost...

Large Language Models (LLMs) like GPT and LLaMA have shown remarkable general capabilities, yet they consistently hit a critical wall when faced with structured symbolic planning . This struggle is especially apparent when dealing with formal planning representations such as the Planning Domain Definition Language (PDDL) , a fundamental requirement for reliable real-world sequential decision-makin...

In this episode, we explore an innovative approach to overcoming the notorious energy and latency bottlenecks plaguing modern Large Language Models (LLMs). The core of generative LLMs, powered by Transformer networks , relies on the self-attention mechanism, which frequently accesses and updates the large Key-Value (KV) cache. On traditional Graphical Processing Units (GPUs), loading this KV-cache...

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—from GPT-3 to Gopher—seemed like a straight line to superior intelligence. But this assumption contains a profound and expensive flaw. This episode reveals the non-obvious truth: many of the world's most powerful LLMs are profoundly undertrained, was...

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 new preference—from a customer service bot that must be concise to a research assistant that must be exhaustive. This is fundamentally broken. Today, we dissect the counterintuitive reason this approach is doomed and reveal a paradigm shift that replaces...

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 become endlessly better at its job? This isn't science fiction; it's the radical premise behind the Darwin Gödel Machine (DGM) , a system that represents a monumental leap toward self-accelerating AI. Most AI today operates within fixed, human-designed ar...

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 incredibly sophisticated illusion ? We move beyond the hype and standard benchmarks to reveal the startling truth about how these models perform under pressure. Drawing from a groundbreaking study that uses puzzles—not standard tests—to probe AI's mi...

Large Language Models have a notorious blind spot: long-term strategic planning. They can write a brilliant sentence, but can they execute a brilliant 10-turn game-winning strategy? This episode unpacks a groundbreaking experiment that forces LLMs to level up or lose. We journey into the complex world of  Settlers of Catan — a perfect testbed of resource management, luck, and tactical foresight—to...

Reward engineering is one of the most brutal, time-consuming challenges in AI—a "black art" that forms the very foundation of how intelligent agents learn. For decades, it's been a manual process of trial, error, and intuition. But what if an AI could learn this art and perform it better than its human creators? In this episode, we dissect EUREKA , a groundbreaking system from NVIDIA...

Imagine an AI that doesn't just write code, but evolves it—learning, adapting, and iteratively improving to conquer challenges that have stumped human ingenuity for over half a century. This isn't science fiction; this is AlphaEvolve , Google DeepMind's revolutionary coding agent that’s reshaping what we thought AI could achieve. Forget one-shot code generation. AlphaEvolve orchestrate...

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 and advancing AI. Forget marketing claims – this episode gives you the backstage pass to the essential field of LLM Evaluation, the engine driving genuine AI improvement. As AI weaves into our lives, from automating tasks to creative endeavors, rigorou...

Large Language Models (LLMs) face significant challenges in effectively using a growing number of external tools, such as those defined by the Model Context Protocol (MCP) . These challenges include prompt bloat and selection complexity . As the number of available tools increases, providing definitions for every tool in the LLM's context consumes an enormous number of tokens, risking overwhel...

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 4. We unpack its innovative "cold start" training procedure, where the general-purpose DeepSeek-V3 is ingeniously used to generate initial training data by recursively decomposing complex problems into manageable subgoals. Discover how thi...

Quality Engineering (QE) professionals are  well-positioned  to transition into AI Improvement Engineering roles due to their deep knowledge of testing, quality assurance, and processes. This transition expands their role significantly – from assuring quality in products to  improving the entire system  that delivers them. The role demands augmenting traditional QE skillsets with knowledge of  AI/...

This episode delves into CaMeL , a novel defense mechanism designed to combat prompt injection attacks in Large Language Model (LLM) agents. Inspired by established software security principles , CaMeL focuses on securing both control flows and data flows within agent operations without requiring changes to the underlying LLM. We'll explore CaMeL's architecture, which features explicit iso...

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 early design principles still echo through today’s cutting-edge AI. From scavenged servers to hyper-optimized global systems, we follow Google's relentless pursuit of scale, speed, and precision, drawing lessons from Jeff Dean’s landmark 2009 WSDM...

[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 Down a Dream ” —a no-fluff, high-octane blueprint for building a career that truly lights you up. Through vivid stories of Bobby Knight, Bob Dylan, and Danny Meyer, Gurley reveals five timeless principles that separate the dreamers from the doers: Find...

[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 level? In this episode, we explore the philosophy of David Ogilvy, one of the greatest advertising minds of all time. Learn about his concept of ' Divine Discontent ' and how it can fuel your ambition, inspire courageous action, and unlock your...