09:52
NVIDIA’s New AI Turns One Photo Into A World That Never Breaks
NVIDIA's Lyra 2.0 can generate a fully explorable, spatially consistent 3D world from a single photograph — and Two Minute Papers hos...
Sort by: Newest Items
There are 355 items in this page
01:20:58
TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google
Cormac Brick, tech lead for Google AI Edge with a decade of experience spanning Intel NPU architecture and Google's Pixel AI features...
12:34
Ship 5x more PRs with OpenAI Symphony
AI Jason provides an in-depth walkthrough of OpenAI's newly open-sourced Symphony framework, which proposes a fundamental rethink of...
29:31
The insane engineering of Deepseek V4
AI Search breaks down the technical architecture of DeepSeek V4 Pro, the latest model from the Chinese AI research lab that has achie...
14:45
How Claude’s Design Agents Work
Sam Witteveen dissects the engineering behind Claude Design — Anthropic's AI-powered design agent running on Claude Opus 4.7 — not to...
24:19
Mastering AI Pricing: Flexible & Agile Monetization — Mayank Pant, Stripe
Mayank Pant, billing solutions architect at Stripe, presented findings from two years of working with AI companies on pricing strateg...
19:18
LLM codegen fails and how to stop ’em — Danilo Campos, PostHog
Danilo Campos, an engineer at PostHog, delivers a frank breakdown of where AI coding agents fail in production — and the concrete fix...
19:22
Replacing 12K LoC with a 200 LoC Skill — David Gomes, Cursor
David Gomes, an engineer at Cursor, delivers a conference talk explaining how the team replaced approximately 15,000 lines of code po...
23:24
Making a 1990s Phone Work Again! Hacking, Firmware, and What’s Inside!
Dave from Dave's Garage documents the restoration of a brand-new, never-installed Nortel Millennium payphone from the 1990s, discover...
02:13:41
The math behind how LLMs are trained and served – Reiner Pope
Dwarkesh Patel interviews Reiner Pope — CEO of chip startup MatX and former Google TPU architect — in a blackboard lecture format des...
20:13
Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI
Maxime Labonne, Head of Pre-training at Liquid AI, delivers a technically rigorous conference talk on the distinct challenges of trai...
23:24
One Login to Rule Them All: Cross-App Access for MCP — Garrett Galow, WorkOS
WorkOS product lead Garrett Galow — formerly of Microsoft Azure and Cloudflare, and whose platform powers authentication for Anthropi...
09:35
Solved: The Bug That Haunted AI Video For Years
Two Minute Papers host Dr. Károly Zsolnai-Fehér breaks down a research paper targeting one of the most persistent failures in AI vide...
10:01
The Hidden Engine Behind DeepSeek V4 – DeepEP V2 and TileKernels Explained
While most coverage of DeepSeek V4 focuses on benchmark scores, Fahd Mirza goes a level deeper to explain the two open-sourced infras...
25:39
Why building eval platforms is hard — Phil Hetzel, Braintrust
Phil Hetzel, head of solutions engineering at Braintrust, delivers a structured conference talk on the practical challenges of buildi...
20:35
Lessons from Scaling GitHub’s Remote MCP Server — Sam Morrow, GitHub
Sam Morrow, the engineer who leads development of GitHub's MCP server, delivered this talk at AI Engineer Europe 2026, sharing hard-w...