Rich Sutton and Khurram Javed discuss their radical vision for AI at Oak Lab, advocating for truly continual learning agents that learn from their own experience, rejecting synthetic data due to the "Big World Hypothesis," and outlining a path to overcome catastrophic forgetting with "continual backprop" for a trillion-parameter, self-maintaining mind, while critiquing LLMs as only a fraction of intelligence.
Priyanka Vergadia, The Cloud Girl, discusses why most companies see no ROI from AI tools, proposing a 7:1 budget split for training over tools. She explains how AI has made "taste" the new ceiling, detailing how to build effective Claude skills by breaking tasks into explicit subtasks with human-in-the-loop oversight. She introduces her 10-20-70 framework for AI budgets, emphasizing the long-term investment needed for employee skilling and community building. Priyanka also shares her transition to full-time entrepreneurship, focusing on product and career storytelling, and reveals her upcoming book on tech storytelling.
Ankit Jain argues that traditional line-by-line code review is defunct, with AI reviewing code that humans no longer read. He asserts that code review's vital, often overlooked, purpose is 'alignment'—knowledge sharing, mentorship, and architectural feedback—which current AI-driven workflows fail to capture. His proposal involves capturing user-AI interaction prompts as acceptance criteria, generating test plans with an 'AI Slop Registry' (codified recurring review comments), and verifying changes against live previews. The new review surface becomes the 'intent and evidence' rather than the code diff, preserving collaboration and ensuring semantic accuracy.
This session provides an in-depth exploration of Loop Engineering, a paradigm shift from manual AI prompting to designing autonomous systems that orchestrate AI agents. Speakers share practical experiences, from building production-grade platforms with automated code generation and adversarial AI reviews to experimental loop structures and foundational infrastructure layers. Key discussions address challenges like managing token costs, preventing agent chaos, and implementing robust verification mechanisms for industrializing software development.
Tom Blomfield of Y Combinator discusses the paradigm shift towards AI-native companies, moving beyond traditional human-centric hierarchies. He introduces the concept of self-improving AI loops—where systems continuously learn and evolve without human intervention—and illustrates this with examples like YC's self-healing data agents and living user manuals. Blomfield explores the vision of 'AI employees with VMs' leading to a 'company brain,' where humans transition to the 'edge' for intuition and real-world interaction. He concludes with practical advice for founders: prioritize token burn over headcount, ensure all data is AI-legible, and leverage AI for strategic simulations like investor calls.
Jon Krohn dissects Alibaba's Qwen 3.8 Max, a 2.4-trillion-parameter Mixture-of-Experts (MoE) model positioned as the largest open-weight release in history if its promised weights ship. The discussion covers its multimodal capabilities, 1M token context window, and performance competitive with Anthropic's Claude Fable 5. Key highlights include its advanced multi-day agentic capabilities and aggressively low pricing ($2 in / $6 out per million tokens), intensifying the AI price war. Krohn also provides critical insights into the safety of using Chinese models, emphasizing data handling practices and the benefits/risks across different deployment scenarios.