Latent Space

Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Eskildsen of Turbopuffer

OpenClaw's Memory Sucks and the fix is simple — Dhravya Shah, Supermemory

Modern AI memory infrastructure requires moving beyond static vector databases toward stateful systems capable of temporal reasoning, knowledge updates, and selective forgetfulness. Traditional RAG and file-system-based approaches often fail to provide true user understanding, leading to context pollution and excessive...

Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup

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

Cursor's Third Era: Cloud Agents — ft. Sam Whitmore, Jonas Nelle, Cursor

Why Every Agent Needs a Box — Aaron Levie, Box

⚡️ Polsia: Solo Founder Tiny Team from 0 to 1m ARR in 1 month & the future of Self-Running Companies

Ben from Polsia discusses Polsia, an AI platform designed to autonomously build and run companies. Polsia enables users to input an idea, and the AI handles product coding, marketing, email campaigns, and competitive research. It operates autonomously, making nightly decisions based on business performance and user fee...

Measuring Exponential Trends Rising (in AI) — Joel Becker, METR

Dylan Patel Explains the AI War While Cooking | In-Context Cooking

The podcast explores the future of AI and semiconductor industry bottlenecks through the lens of chicken fried rice preparation. Dylan Patel, founder and CEO of Semianalysis, shares insights on potential endgame scenarios involving Taiwan and TSMC, including political coups and the impact of export controls on Chinese ...

🔬Max Welling: Materials Underlie Everything

The podcast explores the intersection of AI and material science, particularly regarding climate change and new materials discovery. Max Welling, known for his work on variational autoencoders and graph neural networks, discusses his startup CuspAI and its mission to accelerate materials innovation for a sustainable fu...

Claude Code for Finance + The Global Memory Shortage: Doug O'Laughlin, SemiAnalysis

The End of SWE-Bench Verified — Mia Glaese & Olivia Watkins, OpenAI Frontier Evals

Inside AI’s $10B+ Capital Flywheel — Martin Casado & Sarah Wang of a16z

The current AI investment landscape is defined by a blurring of traditional boundaries between venture and growth stages, as well as infrastructure and application layers. Massive capital requirements for compute power have created a unique "fundraising flywheel" where companies leverage large rounds to secure capabili...

The AI Frontier: from Gemini 3 Deep Think distilling to Flash — Jeff Dean

Jeff Dean, Chief AI Scientist at Google, explores the balance between frontier AI model development and practical deployment. The conversation highlights Google's strategy of maintaining both highly capable and affordable models, leveraging techniques like distillation to transfer capabilities from large models to smal...

🔬Generating Molecules, Not Just Models

⚡️ Reverse Engineering OpenAI's Training Data — Pratyush Maini, Datology

Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell

⚡️Context Graphs: according to the authors — Jaya Gupta, Ashu Garg, Foundation Capital

🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew White

⚡️ Prism: OpenAI's LaTeX "Cursor for Scientists" — Kevin Weil & Victor Powell, OpenAI for Science