AI NEWS: Stripe's Minions, Distillation Attacks on Claude, Cloudflare's Code Mode
Shane and Abhi break down the biggest AI news from the past few days. Anthropic identified industrial-scale distillation attacks on Claude by DeepSeek, Moonshot AI, and MiniMax. Anthropic also released a groundbreaking report analyzing millions of AI agent interactions using Claude. Stripe is shipping 1,300+ AI-generated PRs per week with their Minions system. Code Mode for MCP is becoming a standard part of the MCP ecosystem, and we cover skills benchmarks, trajectory explorer for agent traces, Vercel AI Gateway video support, and more.
Watch on
Episode Transcript
Intro
Anthropic: Distillation Attacks by DeepSeek, Moonshot, MiniMax
Anthropic's Agent Report: 50% Software Engineering, Other Domains Emerging
Claude Code Security in Research Preview
Prompt Auto-Caching with Claude
Stripe Minions: 1,300 PRs/Week
Code Mode for MCP (99.9% Token Reduction)
Amp: The Coding Agent Is Dead
Skills Beat Size: Smaller Models with High-Quality Skills
Quick Hits: Trajectory Explorer, Vercel AI Gateway, Taalas, Google Photoshoot
GitHub Star Party: Superpowers Framework
More episodes
- August 14, 2026Git Wasn't Built for Agents, So Mesa Rebuilt the File System | Agents Hour
- August 13, 2026What Are Agent Plugins, Are We Ready for AI Employees & OpenClaw Hacks a Gym | This Week In AI
- August 10, 2026Building the AI-Native Superhuman for Sales on Mastra - Cedar Copilot | Agents Hour
- August 7, 2026OpenAI vs Anthropic: Who's More Dangerous? Is Google Giving Up? Open Weights Cook | This Week In AI