Why Your AI Agents Don’t Work with Dex Horthy of HumanLayer

Uploaded March 2026 | Updated September 2026, 2 weeks ago

In this episode, we have Dex Horthy, founder and CEO of Humanlayer and the mind behind “context engineering,” joining us to recreate restaurant-style Dan Dan noodles. From his first internship at NASA JPL at 17 to building dev tools for AI engineers, Dex shares how real AI systems are actually built, why most demos don’t translate to production, and what the future of software engineering looks like in the age of coding agents.

We talk about:
• How Dex landed a NASA Jet Propulsion Lab internship at 17
• The origin of “context engineering” and why the term stuck
• Why the top 1% of AI engineers build differently from everyone else
• What AI “slop” actually means
• The “dumb zone” of context windows
• How to build intuition when working with AI models
• Why coding is not the same as shipping real software
• How AI will change the role of software engineers

0:00 - Intro
0:12 - Meet Dex Horthy (Humanlayer) + Cooking Challenge
1:15 - Tasting Dan Dan Noodles
1:25 - How Dex Got a NASA Internship at 17
3:36 - The Origin of “Context Engineering”
6:24 - What AI “Slop” Actually Means
8:06 - From Engineer to Founder
12:54 - How Context Engineering Is Changing
15:23 - The “Dumb Zone” of Context Windows
18:59 - Will AI Replace Software Engineers?
21:27 - Chaotic Final Plating
22:00 - Taste Test: Who Cooked It Better?
24:24 - Judges Decide the Winner

Why Your AI Agents Don’t Work with Dex Horthy of HumanLayer | In-Context Cooking

The AI Memory Problem: Why Long Context Isn’t Enough — Dan Biderman, Engram Co-founder & CEO

The Tension Between AI and Biology Thats Actually Driving Breakthroughs

$Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21 Join us for an exclusive conversation with *Barak Lenz,* CTO of AI21, as he unveils their groundbreaking *Jamba 3B* model - a tiny yet powerful hybrid transformer-state space model designed to bring long context capabilities to edge devices. Barak shares the fascinating journey of how AI21 became pioneers in hybrid architectures, combining attention mechanisms with Mambas state space models to achieve unprecedented efficiency without sacrificing performance. In this deep technical discussion, Barak reveals how the 1:8 ratio of attention to Mamba layers emerged from extensive ablations, why hybrid models are essential for the future of long-context AI, and how Jamba 3B can fit the same context length as much larger models while using a fraction of the memory. He explains why images quickly become long context problems (with just 4 images requiring thousands of tokens) and how this makes hybrid architectures crucial for on-device AI applications. The conversation explores AI21s broader vision for *AI systems over standalone models,* with Barak making a compelling case for why enterprises need model-agnostic orchestration layers that can balance cost, latency, and accuracy. He introduces *Maestro,* AI21s enterprise AI system that treats models as actions with statistical properties rather than monolithic solutions, enabling continuous learning and adaptation without being locked into any single model provider. Drawing from his unique background in algorithmic trading, Barak shares insights on developing frontier models with thousands of GPUs, the importance of world-class engineering in AI research, and why the industry needs to move beyond brute force approaches to reasoning. He candidly discusses the challenges of training at scale, the persistence of optimization issues even with modern architectures, and why good engineering is just as crucial as algorithmic innovation.$

AI Agents Need Computers: 74% MoM Growth, 850K/Day Runs, & New Agent Cloud — Ivan Burazin, Daytona

Prompt Optimization Trends & Future Insights

Marc Andreessen introspects on Death of the Browser, Pi + OpenClaw, and Why This Time Is Different

⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security

Why Every Agent Needs a Box — Aaron Levie, Box