Topic
Google Gemini
7 episodes
-
RAG Explained Simply with a Real Project
A breakdown of Retrieval-Augmented Generation (RAG) using the open-book exam analogy, explaining why traditional LLMs fail on private data, how RAG works internally, and what practical trade-offs exist when building a RAG project.
-
Agentic AI: How to Save on Tokens | Towards Data Science
Cody and Justy examine whether the token-saving techniques in Ida Silfverskiöld's article (prompt caching, semantic caching, lazy-loading, routing, context cleanup) are practical wins or theoretical cost-cutting that introduces real friction. Cody opens skeptical: the savings are real but the tradeoffs are often hidden or underestimated. Justy counters that for production teams already bleeding money on agentic AI, even 20-30% savings justifies the engineering lift. They land on a nuanced take: prompt caching is genuinely low-risk and worth it; semantic caching and aggressive routing are trickier and need honest trade-off audits before deployment.
-
Towards a science of scaling agent systems: When and why agent systems work
A skeptic’s take on Google Research’s paper on scaling agent systems. Cody argues the useful part is not “more agents” but the evidence that coordination only helps when the task structure fits. Justy pushes on why that matters for teams shipping assistants right now, where cost, reliability, and user trust beat demo flair. Together they unpack the five architectures, the strong gains on parallel work, the collapse on sequential planning, and what a solo builder could test this weekend.
-
The Complete Guide to Inference Caching in LLMs
Justy and Cody dig into inference caching for LLMs and why it matters right now for anybody paying real model bills or waiting on sluggish responses. They unpack the three layers from the article — KV caching inside a single generation, prefix caching across requests with identical leading tokens, and semantic caching using embeddings plus vector search to skip model calls entirely. The episode stays grounded in production reality: prompt structure, exact-match requirements, provider behavior, GPU memory trade-offs, and when semantic caching is actually worth the extra moving parts.
-
New framework lets AI agents rewrite their own skills without retraining the underlying model
Episode 277 of Exploring Next covers Memento-Skills, a framework that enables AI agents to rewrite their own skills without retraining the underlying model, and its implications on autonomous agents and enterprise teams.
-
Visual imitation learning: Guidde trains AI agents on human 'expert video' instead of documentation
Guidde raised $50M to solve enterprise AI's 'last mile' problem by training agents on video recordings of human experts, not documentation. Instead of PDFs, they capture rich telemetry—every click, scroll, and DOM change—creating 'digital world models' that let AI navigate complex enterprise software with human-like spatial awareness.
-
Memory: How Agents Learn
In this episode, we dive into the critical aspect of memory in AI agents, exploring how it enables learning and the transformative implications for user experience and system efficiency. We discuss the types of memory—session, user, and learned—and how they contribute to smarter, more effective agents. Join us as we uncover the potential of these technologies and their real-world applications.