Episode 7: Project Vend Update, Hallucinating Neurons, and Year End Reflections

About this episode

In this episode, Shimin and Dan explore the latest advancements in AI coding, including NVIDIA's new models, the implications of AI-generated code, and the outcome of Anthropic's project Vend, AI management of vending machines. They also discuss the significance of multi-agent systems in coding, the concept of vibe coding, and delve into the research on hallucination neurons in large language models. The episode concludes with a year-end review reflecting on the rapid developments in AI technology throughout 2025.

Takeaways

• AI-generated code has been found to create more problems than human code.
• AI in vending machines has led to humorous and unexpected outcomes.
• Multi-agent systems can enhance the coding process by providing diverse solutions.
• H-neurons in LLMs are linked to hallucination and overcompliance.
• Year-end reflections highlight the rapid adoption of AI in the industry.
• The future of AI coding looks promising with ongoing innovations.

Resources Mentioned
NVIDIA Nemotron 3 Family of Models
GLM-4.7: Advancing the Coding Capability
Our new report: AI code creates 1.7x more problems
Project Vend: Phase two
Claude Code Changelog
One Agent Isn't Enough
Vibe Coding
H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
2025 LLM Year in Review

Chapters

• (00:00) - Introduction to AI Coding Landscape
• (05:00) - GLM 4.7 and Chinese AI Models
• (09:27) - Project Vend: AI Vending Machine Experiment
• (13:42) - Using Multiple AI Agents for Coding
• (22:51) - Exploring Agent-Based Approaches
• (30:28) - Deep Dive into Hallucination Neurons
• (36:07) - Dan's Rant: Context Management in AI

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