Collection

Library

Browse your videos and channels

Video Assets

919

Tracked Channels

30

Videos 919 Channels 30

AI Engineer

Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs

5 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI agents are probabilistic systems that must run on deterministic infrastructure; production reliability is an infrastructure/orchestration challenge, not primarily a…

Unread

AI Engineer

Building Great Agent Skills: The Missing Manual

18 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Agent skills are hard to write well because we lack a shared framework; this talk provides a 4-part checklist (Trigger, Structure, Steering, Pruning) to escape 'skill …

Unread

20VC with Harry Stebbings

Bloom Energy CEO: Why We Aren’t in an AI Capex Bubble | Energy Sovereignty & The Future of Power

42 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI's explosive power demand is catalyzing a once-in-150-year transformation from centralized grid electricity to distributed, on-demand digital power at the edge—and B…

Unread

20VC with Harry Stebbings

Bloom Energy CEO: "To lose is something I simply cannot contemplate"

2 min read

## At-a-Glance - Verdict: Skip - Core thesis: Cannot be determined; transcript is corrupted with repetition and placeholder text - Why it matters: Does not matter; transcript extraction failed - Best use: Disregard this …

Unread

AI Engineer

You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs

10 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: As AI commoditizes code-writing, the bottleneck shifts to requirements elicitation and stakeholder communication—'you can't prompt the room'—making analyst/product ski…

Unread

AI Engineer

The Future Is Domain-Specific Agents - Justin Schroeder, StandardAgents

22 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Domain-specific agents—small, specialized agents with isolated contexts that communicate via natural language—will replace the current inheritance pattern of bloating …

Unread

AI Engineer

Frontier results, on device - RL Nabors, Arize

21 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: You can replace expensive frontier LLM API calls with on-device small language models (SLMs) by systematically evaluating tasks, selecting the smallest model that meet…

Unread

AI Engineer

Structuring the Unstructured - Cedric Clyburn, Red Hat

17 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Dockling (Linux Foundation open-source tool) solves enterprise unstructured data processing with local, fast, cheap OCR+layout analysis to extract accurate markdown/JS…

Unread

AI Engineer

User Signal Dies at the Retrieval Boundary - Sonam Pankaj, StarlightSearch

8 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: AI agents fail primarily because retrieval doesn't learn from outcomes—eval feedback dies in dashboards instead of updating agent memory, and StarlightSearch's 'utilit…

Unread

AI Engineer

Using Spec-Driven Development for Production Workflows - Erik Hanchett, AWS

14 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Spec-driven development (writing requirements and design docs before code) significantly improves AI coding assistant outputs by providing structured context and preve…

Unread

20VC with Harry Stebbings

How We Got Fred Wilson, Benchmark and Index to Invest $94M | Why Robinhood's Strategy is Wrong

47 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: FOMO built a social trading app to $550M valuation with 17 people by giving non-founders equity like founders, staying lean, using AI to ship fast, and raising strateg…

Unread

AI Engineer

Recursive Coding Agents - Raymond Weitekamp, OpenProse

16 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: RLMs (Recursive Language Models) represent a paradigm shift in AI agents by unifying tool calling and reasoning through symbolic manipulation of context, and their pri…

Unread

AI Engineer

The Log Is The Agent - Ishaan Sehgal, Omnara

11 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: An agent's identity is its append-only event log, not the model/runtime—making the log the primary durable artifact enables reliability, portability, ownership, and pr…

Unread

AI Engineer

Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co

16 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Single-prompt AI voice systems fail at scale because they conflate four distinct jobs—immutable constraints, situational adaptation, expressive tone, and post-generati…

Unread

More or Less Podcast

Chinese AI Model GLM 5.2 Beating Frontier Models | Meta Glasses, Polymarket Scandal, AI Talent War

43 min read

## At-a-Glance - Verdict: Skim - Core thesis: The highest-signal argument is that fast open-weight models such as GLM 5.2 may already match frontier models for coding while running much faster on rented infrastructure, w…

Unread

AI Engineer

A Genius With Amnesia - Victor Savkin, Nx

14 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Coding agents behave like geniuses with amnesia because they are confined to one repository and one session; an agent-agnostic orchestration layer can overcome both li…

Unread

AI Engineer

Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov

12 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: OpenGov successfully scaled production AI agents (OG Assist) across their government ERP platform by building a custom Effect-native agent loop, standardizing on the A…

Unread

AI Engineer

Turn 10,994 Notes Into Memory - Paul Iusztin, Decoding AI & Louis-François Bouchard, Towards AI

28 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Build a personal AI research OS by combining a deep research algorithm with a file-based, LLM-queryable wiki layer that evolves with your questions, avoiding the compl…

Unread

AI Engineer

The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen

32 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: Role-playing language agents systematically fail by producing anachronistic composites—personas that sound historically authentic but reason from culturally dominant m…

Unread

20VC with Harry Stebbings

Wall St's $725BN AI Question | The Rise of Open Source & How it Threatens OpenAI & Anthropic

75 min read

## At-a-Glance - Verdict: Watch fully - Core thesis: The AI market is entering a phase of margin pressure and competitive disruption: open source (particularly Chinese state-subsidized models like DeepSeek) threatens the…

Unread