Alex Dimakis: The Future of Long-Horizon AI Agents - Episode 21: The Effortless Podcast

In this episode of The Effortless Podcast, Amit Prakash and Dheeraj Pandey are joined by Alex Dimakis for a wide-ranging, systems-first discussion on the future of long-horizon AI agents that can operate over time, learn from feedback, adapt to users, and function reliably inside real-world environments.The conversation spans research and industry, unpacking why prompt engineering alone collapses at scale; how advisor models, reward-driven learning, and environment-based evaluation enable continual improvement without retraining frontier models; and why memory in AI systems is as much about forgetting as it is about recall. Drawing from distributed systems, reinforcement learning, and cognitive science, the trio explores how personalization, benchmarks, and context engineering are becoming the foundation of AI-native software.Alex, Dheeraj, and Amit also examine the evolution from SFT to RL to JEPA-style world models, the role of harnesses and benchmarks in measuring real progress, and why enterprise AI has moved decisively from research into engineering. The result is a candid, deeply technical conversation about what it will actually take to move beyond demos and build agents that work over long horizons.Key Topics & Timestamps 00:00 – Introduction, context, and holiday catch-up04:00 – Teaching in the age of AI and why cognitive “exercise” still matters08:00 – Industry sentiment: fear, trust, and skepticism around LLMs12:00 – Memory in AI systems: documents, transcripts, and limits of recall17:00 – Why forgetting is a feature, not a bug22:00 – Advisor models and dynamic prompt augmentation27:00 – Data vs metadata: control planes vs data planes in AI systems32:00 – Personalization, rewards, and learning user preferences implicitly37:00 – Why prompt-only workflows break down at scale41:00 – RAG, advice, and moving beyond retrieval-centric systems46:00 – Long-horizon agents and the limits of reflection-based prompting51:00 – Environments, rewards, and agent-centric evaluation56:00 – From Q&A benchmarks to agents that act in the world1:01:00 – Terminal Bench, harnesses, and measuring real agent progress1:06:00 – Frontier labs, open source, and the pace of change1:11:00 – Context engineering as infrastructure (“the train tracks” analogy)1:16:00 – Organizing agents: permissions, visibility, and enterprise structure1:20:00 – SFT vs RL: imitation first, reinforcement last1:25:00 – Anti-fragility, trial-and-error, and unsolved problems in continual learning1:28:00 – Closing reflections on the future of long-horizon AI agentsHosts:Amit PrakashCEO & Founder at AmpUp, Former engineer at Google AdSense and Microsoft Bing, with deep expertise in distributed systems, data platforms, and machine learning.Dheeraj PandeyCo-founder & CEO at DevRev, Former Co-founder & CEO of Nutanix. A systems thinker and product visionary focused on AI, software architecture, and the future of work.Guest:Alex DimakisAlex Dimakis is a Professor in UC Berkeley in the EECS department. He received his Ph.D. from UC Berkeley and the Diploma degree from NTU in Athens, Greece. He has published more than 150 papers and received several awards including the James Massey Award, NSF Career, a Google research award, the UC Berkeley Eli Jury dissertation award, and several best paper awards. He is an IEEE Fellow for contributions to distributed coding and learning. His research interests include Generative AI, Information Theory and Machine Learning. He co-founded Bespoke Labs, a startup focusing on data curation for specialized agents.Follow the Hosts and the Guest: Dheeraj Pandey:LinkedIn - https://www.linkedin.com/in/dpandeyTwitter - https://x.com/dheerajAmit Prakash:LinkedIn - https://www.linkedin.com/in/amit-prak...Twitter - https://x.com/amitp42Alex Dimakis:LinkedIn - https://www.linkedin.com/in/alex-dima...Twitter - https://x.com/AlexGDimakis Share Your Thoughts Have questions, comments, or ideas for future episodes?📩 Email us at [e-mail]’t forget to Like, Comment, and Subscribe for more conversations at the intersection of AI, systems, and product design.