25:53
Build AI Systems for Discernment, Not Approval – Angel Ortmann Lee, Duolingo
Angel Ortmann Lee, a software engineer on the security team at Duolingo, argues that the weakest link in most human-in-the-loop AI sy...
Sort by: Newest Items
There are 457 items in this page
14:28
How we taught agents to use good retrieval – Hanna Lichtenberg, Mixedbread AI
Hannah Lichtenberg and Amir, co-founder and agentic search lead at Mixedbread AI, present research on what they call the "knowledge g...
05:27
What’s at the center of Claude’s mind?
Anthropic has published research into what it calls the "J-space" — an internal structure discovered within Claude's neural network t...
22:35
Continual Learning for AI Agents: From Failures to Durable Improvements – Soheil Feizi, RELAI
Soheil Feizi, founder and CEO of RELAI and associate professor of computer science at the University of Maryland, presents a rigorous...
28:54
MCP Apps: Primitives, discovery, and the Future of Software – Pietro Zullo, Manufact, Inc
Pietro Zullo, co-founder of Manufact, delivers a conference talk on MCP (Model Context Protocol) apps — covering the primitives that...
08:06
SpatialClaw – Why Code Is the Right Interface for Spatial AI Agents
Fahd Mirza covers SpatialClaw, a new training-free spatial reasoning agent from researchers at NVIDIA and KAIST that significantly ou...
25:21
Deepseek drops another HUGE breakthrough
AI Search provides a structured technical breakdown of DeepSeek's DSpark system, which the team claims achieves over 6x output throug...
09:01
NVIDIA’s Two-Tower Model Generates Text 2.4x Faster Without Losing Quality
NVIDIA has released NeMo-Tron 2 Tower 30B A3 Base, a 30-billion parameter model that rethinks how large language models generate text...
07:27
This New AI Model Changes Everything
Two Minute Papers host Dr. Koa Eher examines GLM 5.2, the latest open-weight model from the GLM team, arguing it represents a histori...
14:10
Your Agent Failed in Prod. Good Luck Reproducing It. – Tisha Chawla & Susheem Koul, Microsoft
Tisha Chawla and Susheem Koul from Microsoft open with a scenario that will be familiar to anyone running AI agents in production: an...
30:38
The Future Is Domain-Specific Agents – Justin Schroeder, StandardAgents
Justin Schroeder, co-founder of stealth startup StandardAgents, delivers a conference talk at AI Engineer arguing that domain-specifi...
07:14
Deterministic Infra for Non-Deterministic AI Agents – Nishant Gupta, Meta Superintelligence Labs
Nishant Gupta, a software engineering tech lead at Meta Superintelligence Labs, delivers a conference talk arguing that the hard prob...
20:43
Building Great Agent Skills: The Missing Manual
Delivered as a recorded keynote for the AI Engineer World's Fair, this talk by the creator of the popular Matt PCO skills repo introd...
30:14
Agents Building Agents – Alfonso Graziano, Nearform
Alfonso Graziano, tech lead at NearForm and O'Reilly author of "Learning AI Native Software Engineering," presents a structured metho...
15:37
User Signal Dies at the Retrieval Boundary – Sonam Pankaj, StarlightSearch
Sonam Pankaj, CEO and co-founder of Starlight Search, presents Agent RX (Runtime Experience) — a memory layer designed to make AI age...
28:27
The 100-Tool Agent Is a Trap – Sohail Shaikh & Ankush Rastogi, Prosodica
Sohail Shaikh and Ankush Rastogi of Prosodica present research at the AI Engineer conference on a performance failure pattern they ca...