Videos — All · 24 cards

How To Make Better Decisions (with way less uncertainty) - Joe Hudson

1:43:164 min read

Decision paralysis stems from an unwillingness to experience emotional consequences, which dissolves once five to seven core principles guide an iterative portfolio of actions.

Insane GitHub Repos To Actually 10x Claude Video Editing

14:572 min read

Eight specialized open-source GitHub repositories equip AI agents like Claude Code with advanced audio-visual generation, synchronization, and testing workflows for video production.

What My Own Doctor Taught Me About Pain and Happiness, featuring Dr. Chris Good

1:17:395 min read

Total elimination of physical and psychological pain is an impossible objective that magnifies suffering; true well-being comes from reducing resistance through acceptance, managing underlying biological factors, and actively securing small functional victories.

5 Programming Side Quests to Escape Web Dev

5:082 min read

Stepping out of web development into computer science side quests like game development, embedded programming, systems programming, security, and machine learning expands technical skills.

A Valid Key Let an AI Agent Delete Production - Sagar Batchu, Speakeasy

20:403 min read

Unchecked authority rather than model error causes agent failures, making a dedicated control layer that enforces identity, policy, and audit logging mandatory for safe AI deployment.

AI Writes Code Faster Than Your Team Can Review It - Andrew Norrish, Sourcegraph

18:573 min read

AI-driven development increases developer velocity and code volume, but shifts the bottleneck to human code review, resulting in more production incidents and increased SRE toil.

Your AI Pilots Won't Move the P&L. Here's What Will - Adam Nahari, Apollo

15:523 min read

Moving the P&L with AI requires investing five units of change management and end-to-end workflow redesign for every one unit of engineering.

I Don't Fear AI Slop. I Fear Untold Stories - Zack Proser, WorkOS

18:342 min read

Building automated production factories infused with personal craft and domain expertise enables colleagues and children to share untold stories with asymmetric leverage.

I Made a Fruit Fly Review My Code - Nick Nisi, WorkOS

16:372 min read

Automated code review using a simulated fruit fly brain and AI models demonstrates that routine pull request checks can be offloaded, shifting human responsibilities from line-by-line inspection to verifying business logic and context.

These 5 Words Cost 12% of Your Claude Code Usage

5:273 min read

Background agent summaries in Claude Code run every 30 seconds on the full conversation history, accounting for up to 20 percent of total usage costs.

“Having A Stroke Is Like A Mystical Experience” - Robert Greene

9:342 min read

Human perception is artificially bounded by cultural conditioning and neurological filters, but transcendent experiences and evolutionary reflection reveal a connection to the universal cosmos.

Why We Rebuilt Microsoft Office From Scratch for AI Agents - Yijia Liang, Compound AI

15:453 min read

Rebuilding Office suite tools from scratch as headless, AI-native engines enables financial firms to delegate complex, multi-week deal workflows to autonomous agents.

AI Safety Filters Can Be Used Against You

6:342 min read

AI safety filters are frequently weaponized by both attackers and defenders to trigger refusals, effectively blocking frontier closed models from analyzing threat data while open-source models bypass these constraints to complete security tasks.

Most of Your Docs Readers Are Now AI Agents - Hahnbee Lee, Mintlify & Lincoln Murr, Coinbase

18:523 min read

AI agents have rapidly become the primary consumers of developer documentation and internet services, driving companies to prioritize lightweight APIs and autonomous microtransactions over traditional human frontend design.

If Your AI Scores 100%, Your Eval Is Wrong - Ramakrishnan Lokanathan, eslams.com

18:453 min read

Effective AI evaluations for high-stakes production applications require testing entire workflows and continuously increasing test difficulty rather than measuring isolated final answers.

This Gateway Makes Claude Code 30% Cheaper (Context Mode)

7:513 min read

Routing Claude Code sessions through the Context Mode hosted gateway reduces API costs by approximately 30% on data-heavy tasks by folding long command outputs down to essential details.

Your AI Agent Wants Your Data. Here's How to Lock It Down - Jeff Smith, Oracle

21:403 min read

Securing AI agent data access requires implementing authentication, role-based filtering, and pre-packaged report tools directly at the database layer rather than relying on LLM-generated SQL.

Everyone Has the Same AI Models. Here's What Sets Agents Apart - Richmond Alake, Oracle

25:472 min read

Moving beyond standard control planes to implement an intelligence plane with dedicated memory routing, semantic layers, and ontology components allows agents to learn continuously while cutting token consumption and error margins.

I Can Control My PC From Anywhere in the World (JetKVM)

10:072 min read

Integrating an open-source JetKVM device with an ATX extension board allows remote power control and hardware-level desktop management from anywhere via a web browser.

Expelled, Arrested & Somehow Winning At Life - James Smith

1:20:064 min read

Lasting resilience comes from decoupling personal worth from external performance metrics while calculating the minimal baseline needed to keep your head above water.

Escaping the Trap of Modern Life

7:102 min read

Eliminating phone use during the first hour of the day protects neurocognitive programming and allows personal meaning to emerge.

78% Wanted This AI Feature. Almost Nobody Used It - Supriya Subudhi, Bumble

14:443 min read

A positive A/B test result for a generative AI feature only marks the beginning of product development, as high user interest does not guarantee actual adoption or scalable unit economics.

The Best Git Worktree Tool I've Used (Worktrunk)

7:142 min read

WorkTrunk streamlines multi-agent development workflows by replacing complex multi-step Git commands with single-line operations like wt switch and wt merge.

When Running Your Own AI Models Beats Paying for APIs - Steven Latré, imec

18:303 min read

Transitioning from commercial APIs to self-hosted open-weight models for long-horizon agentic tasks reduces overall costs by 25% when hardware utilization thresholds and harness token efficiency are properly optimized.