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

This week, Rahul, Shimin, and Dan covers Claude Code's new channels and scheduling features, a Meta security incident caused by AI-generated advice, Anthropic's survey of 81,000 people on AI expectations, Dan's vibe-coded vector memory CLI project, a deep dive on the paper "Thinking, Fast, Slow and Artificial" about cognitive surrender to AI, a rant about AI tokens as employee compensation, and bubble watch updates including NVIDIA's trillion-dollar demand projections and OpenAI shutting down Sora.

Takeaways:

• Claude Code is rapidly absorbing community-developed workflows — the moat may only be in the general model capabilities, not tooling
• The Meta incident illustrates the emerging pattern of AI-caused production incidents and the need for process guardrails around agent usage
• Cognitive surrender to AI creates a widening gap: those with high need-for-cognition benefit more while those who dislike effortful thinking defer even more
• AI confidence inflation (12 percentage point boost) may stem from treating AI like authoritative reference material (encyclopedias, Wikipedia)
• Historical technology resistance (Socrates on writing, farmers on tractors) suggests the battle against AI adoption may already be lost
• OpenAI shutting Sora just 4 months after a 3-year Disney partnership signals deeper financial or strategic issues

Resources Mentioned
Push events into a running session with channels
Perhaps not Boring Technology after all
Meta is having trouble with rogue AI agents
What 81,000 people want from AI
Dan's vec-memory-cli
Thinking—Fast, Slow, and Artificial
Are AI tokens the new signing bonus or just a cost of doing business?
Jensen Huang just put Nvidia’s Blackwell and Vera Rubin sales projections into the $1 trillion stratosphere
Accelerated FOMO in the Age of AI
OpenAI shutters AI video generator Sora in abrupt announcement

Chapters
Connect with ADIPod

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

This week, Dan, Shimin & Rahul covers Meta's struggles with its delayed "Avocado" AI model and potential Gemini licensing, NVIDIA's enterprise-ready NemoClaw fork of OpenClaw, SWE-bench analysis showing PRs wouldn't pass human review, prompting superstitions and developer identity, the 8 levels of agentic engineering, mainstream media framing of AI coding, legal liability for agent-written code, and a deep dive into LLM neuroanatomy where a researcher topped leaderboards by repeating model layers without changing weights.

Takeaways:

• Meta may end up licensing Gemini despite massive AI investment — mirroring Apple's path
• SWE-bench failures were mostly code quality, not functionality — suggesting good enough may be good enough with proper agents.md
• A coworker analyzed 4.5 years of PRs to create a personalized coding style document for AI priming
• The fastest software paradigm adoption cycle ever may be the claw/agent paradigm
• Legal frameworks and insurance haven't caught up to agent-written code shipping to production
• Repeating later model layers (the "thinking" layers) can boost performance without fine-tuning — raising questions about whether chain-of-thought reasoning is essentially exercising these layers repeatedly
• Developers compared to ancient Egyptian scribes — language literacy as leverage

Resources Mentioned
Meta Delays Rollout of New A.I. Model After Performance Concerns
NVIDIA NemoClaw
Research note: Many SWE-bench-Passing PRs Would Not Be Merged into Main
The Collective Superstitions of People Who Talk to Machines
The 8 Levels of Agentic Engineering
Coding After Coders: The End of Computer Programming as We Know It
Built by Agents, Tested by Agents, Trusted by Whom?
LLM Neuroanatomy: How I Topped the LLM Leaderboard Without Changing a Single Weight

Chapters

• (00:00) - Introduction to AI in Software Development
• (02:42) - Meta's AI Model Delays and Market Position
• (09:51) - NVIDIA's New AI Developments
• (13:58) - Benchmarking AI Models and Code Quality
• (19:00) - Techniques Corner: AI Prompting and Creativity
• (22:56) - The Evolution of Coding and Creativity
• (28:46) - Levels of Agentic Engineering
• (34:58) - Mainstream Perspectives on AI and Software Development
• (43:00) - Trusting AI-Generated Code
• (44:40) - Metrics for Success in Autonomous Teams
• (46:59) - Legal and Ethical Implications of Autonomous Code
• (50:21) - Innovations in Language Model Architectures
• (01:01:02) - User Experience Challenges in Tech Development
• (01:03:47) - Market Predictions and Financial Insights

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