Informazioni su questo podcast
YAAP brings you practical conversations with the people actually building generative AI solutions. No hype, no sales pitches, just honest discussions about challenges, solutions, and lessons learned.
Listen to developers and engineers share what works, what doesn't, and what they wish they'd known sooner. Simple, useful insights for anyone working with AI — hosted by AI21's Yuval Belfer.
Episodi
I 20 episodi più recenti su 25
- OpenAI Banned Me for Building This · 17 min · Episodio 26Most agent-browser tools bolt on through MCP. Corey J. Gallon, Managing Director at Rexmore, ripped that out. He built Chrome Agent, which talks to Chrome directly over the…
- Your Code Doesn't Need to Be Readable Anymore · 22 min · Episodio 25Geoffrey Huntley hasn't hand-written code in over two years. He's the guy behind the Ralph Wiggum technique, he thinks Git is end of life, and he's rebuilding source control…
- The Model Routing Paradigm That Changed My Mind · 21 min · Episodio 24Model routing sounded solved: cheap stuff to the small model, hard stuff to the big one. Turns out that's how you blow your budget. Tomás Hernando Kofman, founder of Not Diamond…
- Every Learner Gets Their Own Andrew · 22 min · Episodio 23The 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…
- Everything But the Model: Harness Engineering · 27 min · Episodio 22Everything 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…
- Chunking Isn’t Dead. One Size Doesn’t Fit All · 10 min · Episodio 21Chunking 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…
- Stop Shipping Agents With Chat UIs · 36 min · Episodio 20Chat 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”…
- MCP Was Built for Tools, Not for Agents That Write · 22 min · Episodio 19MCP 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…
- Why AI Leaderboards Miss the Point · 57 min · Episodio 18Leaderboards 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…
- The Agent Swarm Fallacy · 30 min · Episodio 17Running 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…
- This Deep Research Agent Ignored the Benchmark and Still Won · 30 min · Episodio 16Tavily 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…
- Don’t Learn Distributed Systems. Just import ray · 31 min · Episodio 15You 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…
- GenAI Meets Wall Street: Why Every Bank Thinks It’s a Snowflake · 36 min · Episodio 13Banks 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…
- Everyone’s got the same model. Now what? · 31 min · Episodio 12Everyone’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…
- The House That Builds Builders – The Origin Story of AGI House · 11 min · Episodio 11Three 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…
- Scraping Without Getting Sued (Or Falling Asleep) · 49 min · Episodio 10Everyone (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…
- The Judge Model Diaries: Judging the Judges · 30 min · Episodio 9Your 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…
- RLVR Lets Models Fail Their Way to the Top · 49 min · Stagione 1 Episodio 8Think 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…
- RAG Is Not Solved – Your Evaluation Just Sucks · 44 min · Stagione 1 Episodio 6RAG 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…
- The Call Is Coming From Inside the Agent (And It Has Your Credentials) · 50 min · Stagione 1 Episodio 5The 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…








