{"version":1,"type":"rich","provider_name":"Libsyn","provider_url":"https:\/\/www.libsyn.com","height":90,"width":600,"title":"#326 Zuzanna Stamirowska: Inside Pathway's Post-Transformer Architecture Designed for Memory and On-the-Fly Learning","description":"This episode is sponsored by tastytrade. Trade stocks, options, futures, and crypto in one platform with low commissions and zero commission on stocks and crypto. Built for traders who think in probabilities, tastytrade offers advanced analytics, risk tools, and an AI-powered Search feature.  Learn more at https:\/\/tastytrade.com\/ This episode dives into why Pathway\u2019s Baby Dragon Hatchling (BDH) might mark the beginning of the post-transformer era in AI. Zuzanna Stamirowska, Pathway\u2019s CEO and co\u2011author of BDH, explains why today\u2019s transformer-based LLMs hit a wall on long-horizon reasoning, how memory and synaptic plasticity are built directly into BDH\u2019s architecture, and what that means for continual learning, hallucinations, and \u201cgeneralization over time.\u201d The conversation ranges from complexity science and brain-inspired computation to practical implications for real-world, small-data, and safety\u2011critical applications.   Stay Updated: Craig Smith on X: https:\/\/x.com\/craigss Eye on A.I. on X: https:\/\/x.com\/EyeOn_AI (00:00) The Core Problem: Why Today\u2019s AI Lacks Memory (03:16) Pathway\u2019s Mission to Bring Memory Into AI (04:53) Zuzanna\u2019s Background in Complexity Science (10:30) Why Transformers Reset Like \u201cGroundhog Day\u201d (14:34) The Brain-Inspired Dragon Hatchling Architecture (23:59) How the Network Learns and Builds Connections (37:38) Performance vs Transformers on Language Tasks (49:37) Productizing the Technology With NVIDIA and AWS (54:23) Can Memory Solve AI Hallucinations? ","author_name":"Eye On A.I.","author_url":"http:\/\/www.eye-on.ai","html":"