Collection

Library

Browse your videos and channels

Video Assets

919

Tracked Channels

30

Videos 919 Channels 30

Every

How to Build a Multi-Agent Review Swarm

9 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: A coding agent becomes materially more useful when it operates from the company’s canonical context, executes remotely, and is governed by a multi-model, domain-specif…

Unread

AI Engineer

Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex

58 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Codex becomes substantially more useful when treated not as a chat-based coding assistant but as a persistent, context-rich operating system of skills, memory, schedul…

Unread

AI Engineer

Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs

13 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Long-horizon agents need to be evaluated in economically realistic, open-ended environments because standard simulations miss both real-world performance failures and …

Unread

AI Engineer

Everything Is a Rollout — Alex Shaw + Ryan Marten, Terminal-Bench, Harbor, Laude Institute

16 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Agent systems should be developed like machine-learning systems: treat their behavior as empirically measured rather than deterministic, and make sandboxed rollouts, t…

Unread

Sweat Equity

If You Don't Understand Luxury, You Don't Understand Business

48 min read

## At-a-Glance - Verdict: Skim - Core thesis: Luxury wins when a business designs a complete, operationally reliable experience for a narrowly defined customer—not merely an expensive product or amenity—and then makes th…

Unread

20VC with Harry Stebbings

Frontier Labs Threatened by Kimi? Should the US Ban Chinese Open-Source Models & Stripe Buys PayPal

73 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Cheap, near-frontier Chinese open-weight models are accelerating model commoditization, making routing, trusted inference, domain-specific tuning, and AI infrastructur…

Unread

My First Million

The oldest trick in the book to make your first million

46 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Durable fortunes are built by owning indispensable bottlenecks, compounding control over time, creating demand around new capabilities, and treating AI-driven abundanc…

Unread

Every

Compound Engineering Now Works Better in a Multi-Model World

41 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Compound Engineering should operate as an outcome-oriented, repository-based learning system that uses human judgment at the start and end of work while routing planni…

Unread

AI Engineer

Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer

17 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI coding harnesses, agent loops, tests, and automated review can accelerate implementation, but they cannot currently prevent long-term codebase degradation because c…

Unread

AI Engineer

Notion's Token Town — Sarah Sachs, Notion

18 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI product companies avoid becoming "token-poor" by treating model access as a volatile commodity: preserve multi-provider optionality, route work by end-to-end cost/c…

Unread

Every

OpenAI’s Codex Workflows for Knowledge Work

26 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: OpenAI positions the combined ChatGPT/Codex environment as an operating system for knowledge work: agents can progressively absorb a worker's recurring processes, oper…

Reading

Every

Behind Our Largest Subscription Revenue Increase

34 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Every argues that the highest-leverage AI workflow is not replacing judgment but building connected, compounding agent loops that automate execution across specialized…

Unread

AI Engineer

Better Agent Auth — Bereket Habtemeskel & Paola Estefania, Better Auth

24 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Agent systems should stop handing agents a user's standing credentials and instead treat every agent as an identifiable principal with narrowly granted, revocable capa…

Unread

AI Engineer

Claude for Long-Horizon Tasks — Lance Martin, Anthropic

18 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Long-horizon asynchronous agents require more than a capable model: they need durable state, decoupled execution and credentials, independent verification loops, self-…

Unread

AI Engineer

Thinner Agents on a Smarter Substrate: The Ontology-based Semantic Layer — Emil Eifrem, Neo4j

8 min read

## At-a-Glance - Verdict: Skim - Core thesis: Enterprise agent systems should shift from individually data-wired “thick agents” to thin agents that operate over a shared, governed ontology-based semantic layer linking bu…

Unread

My First Million

I spent a day with a blue-collar millionaire in NYC

17 min read

## At-a-Glance - Verdict: Skim - Core thesis: Restoring high-end New York brownstones can produce substantial dollar profits and personal pride, but it is a slow, capital-intensive, owner-dependent business where permitt…

Reading

AI Engineer

The Desktop Frontier — Ahmad Osman, Osmantic

10 min read

## At-a-Glance - Verdict: Skim - Core thesis: Open-weight models are improving in capability per parameter fast enough that increasingly capable agentic and reasoning workloads will move from cloud infrastructure to loca…

Unread

AI Engineer

Your agent architecture has a half-life of 6 months — Dan Farrelly, CTO, Inngest

13 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Because models, prompts, tools, and sandbox patterns churn rapidly, agent systems should isolate a durable execution layer—responsible for state, retries, orchestratio…

Unread

AI Engineer

2026 State of AI Engineering — Barr Yaron, Amplify Partners

14 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI engineering is moving from experimentation to operational deployment: teams are running multi-model, cost-constrained systems with increasingly write-enabled agents…

Unread

20VC with Harry Stebbings

The Open-Source AI Reality | How Token Costs Will Fall 10X & Usage Will Explode 100X | Lin Qiao

54 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Lin Qiao argues that AI will not consolidate around a few general models: falling inference costs, open-weight models, and enterprise-private data will produce million…

Reading