Unsupervised Learning x Latent Space Crossover Special

The podcast explores recent surprises and future trends in AI, particularly focusing on open source models and AI engineering. The speakers were surprised by the speed at which open source models, especially DeepSeek, caught up to closed source models, though they debate whether this is sustainable. They also discuss the underperformance of low-code builders in the AI builder market, attributing it to a lack of fresh perspectives unburdened by existing paradigms. The conversation covers the overhyping of agent frameworks and the underhyping of memory/stateful AI. They identify coding agents, support agents, and deep research as areas with product market fit, while also considering the potential of AI in education and voice AI applications. The discussion touches on defensibility at the app layer, emphasizing network effects and brand building.