This week Rahul, Shimin, and Dan returns after a two-week break to cover the leaked Claude Code CLI source code, new model releases (Qwen 3.6 and Gemma 4), Mario Zechner's essay on slowing down with AI-assisted coding, a fun segment on unexpected things AI knows about each host, and two deep dives: Anthropic's research on emotion concepts in LLMs and a paper on how sycophantic AI decreases pro-social intentions.

Takeaways:

• Claude Code's dual-track permission system uses both rule-based and ML classifier for destructive bash command
• "Cognitive bankruptcy" — when cognitive debt interest payments come due and you can't pay
• AI sycophancy parallels social media echo chambers; no market incentive to fix it
• On-device models like Gemma 4 could save cloud costs by handling routine tasks (e.g., agent heartbeats)
• Copilot's terms of service classify it as "for entertainment purposes only"

Resources Mentioned
Entire Claude Code CLI source code leaks thanks to exposed map file
I Read the Leaked Claude Code Source — Here's What I Found
The Claude Code Source Leak: fake tools, frustration regexes, undercover mode, and more
Claude Code Unpacked
Qwen3.6-Plus: Towards Real World Agents
Gemma 4 Announcement
Thoughts on slowing the fuck down
Emotion concepts and their function in a large language model
Sycophantic AI decreases prosocial intentions and promotes dependence

Chapters

• (00:00) - Introduction and Host Updates
• (01:45) - Cloud Code Source Code Leak
• (12:49) - New Model News and Open Source Developments
• (20:51) - Post-Processing and AI Anxiety
• (25:35) - Unexpected Insights from AI
• (33:12) - Exploring Emotional Concepts in AI
• (39:15) - The Dangers of Sycophantic AI
• (52:39) - Concluding Thoughts and Future Considerations

• Email us at humans@adipod.ai you have any feedback, requests, or just want to say hello!
• Checkout our website www.adipod.ai