Summaries of Latent Space Videos 📚

Priscilla Chan and Mark Zuckerberg: Frontier AI + Virtual Biology To Solve All Diseases

What Are Code Agents and Why Do They Beat JSON Agents?

⚡️ARC-AGI-3: The Interactive Reasoning Benchmark

What Makes Modal a Game-Changer for AI Engineers?

How Claude 3.5 Sonnet Builds Coding Agents

How Can Generative AI Simulate Alternate Worlds?

What Is Cog and How Does It Simplify AI Deployment?

The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa)

Why Did Google Miss the Mark on GPT-3 Development?

What Are Large Language Models and Their Applications?

How Cube Transformed Data Access with AI

The State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]

How to Enhance Language Models with Long Context Learning

How Do Liquid Neural Networks Scale Efficiently?

What Are the Four Main Battles in the AI Stack?

How to Create a Podcast Using AI with Wondercraft.ai

The End of Finetuning — with Jeremy Howard of Fast.ai

What Makes RAG a Game-Changer for AI Models?

Bee AI: The Wearable Ambient Agent

What Is GPT-1 and How Does It Work?

The AI Agenda: GPT5 leaks and the business of AI News — Steph Palazzolo, The Information

How is AI Transforming Software Development?

⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect

What Are the Key Trends in AI Development?

What Is Together AI's Vision for Open AI Systems?

LIVE from GTC: DGX Spark Insides First Look

How Does Suno Generate Original Music with AI?

How Chai Crowdsources Better AI Companions

0 to over $8M ARR in 2 months as a Claude Wrapper (Bolt.new, Qodo)

How Does Context Engineering Improve AI Search?

What Happens During a 200K Token AI Inference?

How to Use ChatGPT Codex for Software Engineering

⚡️Claude Sonnet 4.5 and Anthropic's roadmap for Agents and Developers — Mike Krieger, Anthropic

How Can AI Revolutionize Gaming Strategies?

What Makes AI Agents Unreliable Right Now?

How Does RLVR Train Reasoning and Agent Models?

The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert

How to Make AI Play Pokémon Games

DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever

Why AI Needs Models Built for Software, Not Chat

What Is the Normsky Architecture for AI Coding Agents?

LLM Asia Paper Club Survey Round

Better Data is All You Need — Ari Morcos, Datology

What makes O1 good for prompts and coding tasks

Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI

DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)

Taste is your Moat (Dylan Field of Figma)

What is Instructure and How It Empowers Developers?

How Does Factory AI Automate Enterprise Coding?

2024 in Post-Transformer Architectures: State Space Models, RWKV [Latent Space LIVE! @ NeurIPS 2024]

What Is Playground V2 and How Does It Enhance Graphic Editing?

Answer.ai & AI Magic with Jeremy Howard

Terminal-Bench: Pushing Claude Code, OpenAI Codex, Factory Droid, et al to the limits

How to Improve Open Model Pretraining at Scale

AI Engineering for Art - with comfyanonymous

How to Transition from Researcher to AI Leader

The new OpenAI Agents Platform: CUA, Web Search, Responses API, Agents SDK!!

Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire

How Do Language Agents Reason and Use Tools?

What Challenges Are GPU Poor Companies Facing?

What Is Cline? The Open-Source AI Coding Agent Explained

What Is RWKV and How Does It Compare to Transformers?

How Do OpenHands Coding Agents Use Tools? Best of 2024 in Agents with Prof. Graham Neubig (#1 on SWE-Bench Full, OpenHands/AllHands)

⚡ Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules + AIE CODE Preview

⚡️ The State of AI Engineer Hiring: Cheating, AI Adoption,Junior Devs — Vivek Ravisankar, HackerRank

How to evaluate AI agents in Factorio learning environment

How does RL verify science data in wet labs?

How Do Open Source Personal AIs and Voice Bots Work?

Production AI Engineering starts with Evals

The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org

How Does OpenAI Scale AI Research Toward AGI?

How to Build AI Agents with Lindy: A Live Demo

How Does OpenCode Improve Terminal Coding?

AI Video Is Eating The World — Olivia and Justine Moore, a16z

What Is Tiny Grad and How Does It Improve AI Development?

What Is Context Engineering for AI Agents?

Will Bryk on Building Exa's Neural Search Engine

Why Did Sourcegraph Replace Cody With Amp Code?

How to Train Open-Source Agentic RL Models Like o3

Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)

How Positron AI Accelerates Transformer Inference

How NotebookLM Was Made

Claude Code: Anthropic's CLI Agent

The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1

llm.c's Origin and the Future of LLM Compilers - Andrej Karpathy at CUDA MODE

Information Theory for Language Models: Jack Morris

How is Elicit Revolutionizing AI Research Assistance?

Can Open Source Models Outperform GPT-4?

Why is everyone cloning Deep Research?

How Language Models Transform Finance Today

The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot

How Does LLM Distillation Cut Inference Costs?

Raycast: Your AI Automation Assistant

What is an RL environment? w/ Nous Research's Roger Jin

How Does FlashAttention-2 Make Transformers Faster?

The Creators of Model Context Protocol

GPT 4.1: The New OpenAI Workhorse

Building AGI in Real Time (OpenAI Dev Day 2024)

SF Compute: Commoditizing Compute

⚡️Math Olympiad gold medalist explains OpenAI and Google DeepMind IMO Gold Performances

The Utility of Interpretability — Emmanuel Amiesen