YAAP (Yet Another AI Podcast)

Every Learner Gets Their Own Andrew

The video course had a good run. Ryan Keenan from DeepLearning.ai thinks it's over. In this episode, recorded live at AI Dev 26 in San Francisco, Yuval sits down with Ryan to talk about what replaces the current online c

Everything But the Model: Harness Engineering

Everything you need to know about harness engineering, in less than 30 minutes. In this episode, Yuval sits down with Mike Chambers from AWS to unpack harness engineering - the term that's quietly taken over the AI devel

Chunking Isn’t Dead. One Size Doesn’t Fit All

Chunking is still one of the least-discussed but most decisive parts of RAG. In this episode, we break down why no single chunk size works for all questions, how different queries benefit from different window sizes, and

Stop Shipping Agents With Chat UIs

Chat was a great prototype. It’s a terrible product. In this episode, Yuval sits down with CopilotKit co-founder Atai to unpack why most agentic apps stall at “chat + vibes”, and why the real bottleneck in production AI

MCP Was Built for Tools, Not for Agents That Write

MCP standardized tool calling for agents but breaks down once agents start mutating state. In this episode, Yuval sits with Eran Gat from AI21 to dig into what happens when writing agents run in parallel, why shared envi

Why AI Leaderboards Miss the Point

Leaderboards reward “best average score.” Real users reward “answer fast, don’t hallucinate, don’t bankrupt me.” In this special deep dive episode, AI21’s CTO Barak Lenz walks through four gaps between what models can do

The Agent Swarm Fallacy

Running multiple agents can improve quality. Doing it right is the hard part. This time we look at the Agent Swarm Fallacy: the idea that throwing more agents at a problem automatically makes systems better. Yuval sits w

This Deep Research Agent Ignored the Benchmark and Still Won

Tavily built a Deep Research Agent with production in mind. Something they could actually scale. So they did the unsexy work. They went through millions of agent logs, found where tokens were being wasted, and optimized

Don’t Learn Distributed Systems. Just import ray

You wanted to build an agent. You ended up debugging GPUs, scaling workers, and chasing OOMs. In this episode of YAAP, Yuval sits down with Linda from Anyscale to unpack why Ray exists and how it helps AI teams scale wit

GenAI Meets Wall Street: Why Every Bank Thinks It’s a Snowflake

Banks love GenAI. They just don’t trust it. Yet. In this episode of YAAP, Yuval talks with Renee Lau from AWS, a financial services industry specialist who works hands on with banks, insurers, and hedge funds as they try

Everyone’s got the same model. Now what?

Everyone’s building on the same foundation models. So how do you stand out? For Imagen AI, the answer isn’t bigger models, it’s smarter loops. CEO Yotam Gil joins Yuval to unpack how personalization, workflow integration

The House That Builds Builders – The Origin Story of AGI House

Three years ago, it was just a house full of friends geeking out about AI. Today, it’s where researchers, founders, and engineers collide — and where hackathon demos turn into real startups. In this episode, Yuval sits d

Scraping Without Getting Sued (Or Falling Asleep)

Everyone (and we do mean EVERYONE) needs data, and the web is the largest database humanity has ever built. But tapping into it at scale requires more than technical skills. If your product touches web data, scraping isn

The Judge Model Diaries: Judging the Judges

Your LLM gave a great answer. But who decides what “great” means? In this episode, Yuval talks with Noam Gat about judge language models — reward models, critic models, and how LLMs can be trained to rate, rank, and crit

RLVR Lets Models Fail Their Way to the Top

Think you know fine-tuning? If your answer is RLHF, you don’t. In this episode, Itay, who leads the Alignment group at AI21, gives a no-fluff crash course on RLVR (Reinforcement Learning with Verifiable Rewards), the met

RAG Is Not Solved – Your Evaluation Just Sucks

RAG Is Not Solved – Your Evaluation Just Sucks Your RAG pipeline is passing benchmarks, but failing reality. In this episode, Yuval sits down with Niv from AI21 to expose why most RAG evaluation is fundamentally flawed.

The Call Is Coming From Inside the Agent (And It Has Your Credentials)

The Call Is Coming From Inside the Agent (And It Has Your Credentials) You’ve shipped your first agent. It works. It’s useful. It might also be a security liability you don’t even know about. In this episode, Yuval talks

Building Enterprise RAG: Lessons from 2+ Years of Production Deployments

Building production AI systems is hard — especially when you're pioneering entirely new categories. In this episode, Yuval speaks with Guy Becker, Group Product Manager at AI21, to trace the evolution from task-specific

Trailer

You Can’t Have an Agent Without a Plan: What 90% of ’Agents’ Are Missing

Everyone's talking about AI agents, but most of what we call "agents" are just workflows in disguise. Real autonomous agents require planning. And that, changes everything. In this episode, Yuval speaks with AI21's Algo