Trending right now
World Collapse Expert (Ian Bremmer): The Real Crisis Is What Comes After Trump
Is the world on the brink of collapse, and what comes next after a seismic shift in global leadership? Ian Bremmer lays out the stark reality.
Alex Imas on Why Economists Might Be Getting AI Wrong
Are economists miscalculating AI's true impact? Discover why the speed of adoption and job task interconnectedness could reshape our economic future faster than we think.
Our Tax System Should Make You Furious
Is the tax system rigged against you? This episode reveals how the ultra-wealthy pay minimal taxes while you pick up the tab.
#240 - Project Glasswing, Claude Mythos, GLM-5.1, emotion concepts
From AI finding zero-day vulnerabilities to data centers becoming military targets – the latest AI news is stranger and more critical than fiction.
Gadget Prices Are Getting Ridiculous
Are you feeling the pinch of rising gadget prices? MKBHD dives into why your favorite tech is getting ridiculously expensive.
Viewing Podcast: Podcast
AI
Arts
Business
Crypto
Finance
Health
History
Interviews
Investing
Macro
Misc
News
Politics
Product
Programming
Science
Social
Startups
Technology
VC
From journalist to iOS developer: How LinkedIn’s editor builds with Claude Code | Daniel Roth
- The core of the workflow involves using a "dueling agent" system with named AI personas like "Bob the builder" and "Ray the reviewer" to collaboratively build software.
- A key technique for maintaining context and learning involves meticulously logging all interactions and plans into markdown files, which serve as a persistent memory for the AI.
- The speaker, coming from a non-technical background, views their role in this process as a "picky customer" who provides critical feedback and direction, rather than a traditional project manager or architect.
5 OpenClaw agents run my home, finances, and code | Jesse Genet
- AI agents can be leveraged to significantly reduce the manual effort involved in organizing personal information, such as homeschool logs and curriculum materials, by processing photos and structured data.
- The concept of "agent collaboration" is explored as a sophisticated method for managing multiple AI agents, with specific roles and carefully partitioned access to data and functionalities, akin to managing human employees.
- AI agents can bridge the gap between digital and physical worlds by enabling actions like printing materials from voice commands, thus reducing friction in daily tasks and allowing users to step away from their computers.
Claude Opus 4.6 vs. GPT-5.3 Codex: How I shipped 93,000 lines of code in 5 days
- Claude Opus 4.6 has been released, boasting a 1 million token context window and improvements in planning and long-running agentic tasks, though some benchmarks showed a slight decrease.
- The new "Agent Teams" feature in Claude Code allows multiple specialized AI agents to collaborate on complex tasks, significantly enhancing parallel processing and problem-solving capabilities.
- Coinciding with Claude Opus 4.6's release, GBD 5.3 CodeX also launched, and initial comparisons suggest CodeX excelled in UI styling and aesthetic details, while Opus 4.6 had a smoother initial setup and demonstrated the power of Agent Teams.
How this PM uses MCPs to automate his meeting prep, CRM updates, and customer feedback synthesis | Reid Robinson (Zapier)
- MCPS, or "app integrations for AI tools," allow users to create collections of tools from various apps and give AI models access to them for enhanced functionality.
- Zapier's approach to MCPS focuses on enabling AI tools to access knowledge within user applications and perform actions within those apps, simplifying complex workflows.
- Using AI creatively, such as for family calendar planning with photo input or generating personalized children's songs, can significantly simplify personal tasks and spark joy.
I gave Clawdbot (now Moltbot) access to my computer, calendar, and emails: Here’s what happened
- Claudebot is a powerful open-source AI agent that can be installed locally or in the cloud, offering advanced personal productivity but also raising significant security concerns due to its broad access capabilities.
- Setting up and using Claudebot proved to be a complex and sometimes frustrating experience, requiring technical setup and careful prompting to avoid errors like impersonation or incorrect scheduling.
- The speaker highlights a tension between the potential of autonomous AI agents for tasks like research and scheduling, and the current limitations in user-friendliness, security, and reliable execution, suggesting a need for more polished consumer and enterprise versions.
Claude Code for product managers: research, writing, context libraries, custom to-do system, and more | Teresa Torres
- The speaker uses Claude Code and Obsidian to create a personalized task management system, enabling them to quickly add, query, and organize tasks via slash commands.
- A daily research digest is integrated into the task management workflow, summarizing academic papers on chosen topics to help the speaker stay informed and engage in market conversations.
- A meticulously organized "LLM context" vault of small, focused files allows Claude to access relevant information for specific tasks, enabling efficient and "lazy" prompting.
No more episodes to load