An expert overview of post-training techniques for language models, covering the entire workflow from data generation and curation to advanced algorithms like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Reinforcement Learning (RL), along with practical advice on evaluation and iteration.
This talk introduces Anaximander, a system designed to bridge the gap between traditional, GUI-driven Geographic Information System (GIS) workflows and modern, code-heavy machine learning practices. Anaximander integrates geospatial foundation models directly into QGIS, allowing experts to interactively orchestrate, run, and evaluate models for tasks like semantic segmentation and object detection on satellite imagery.
At Applied Compute, efficient Reinforcement Learning is critical for delivering business value. This talk explores the transition from inefficient synchronous RL to a high-throughput asynchronous 'Pipeline RL' system. The core challenge is managing 'staleness'—a side effect of in-flight weight updates that can destabilize training. The speakers detail their first-principles systems model, based on the Roofline model, used to simulate and find the optimal allocation of GPU resources between sampling and training, balancing throughput with algorithmic stability and achieving significant speedups.
Ben Luria, CEO of Hirundo, discusses the critical need for machine unlearning, framing it as a form of "AI neuro-surgery" for enterprise AI. He explains how this technique directly modifies model weights to remove unwanted data and behaviors, addressing core risks that superficial solutions like guardrails cannot solve.
State Space Models (SSMs) are emerging as a powerful and efficient alternative to Transformers for handling sequential data. Aaron Baughman explains the core concepts of SSMs, their mathematical foundations, and how architectures like S4 and Mamba address the memory and scalability challenges inherent in Transformers, leading to a new generation of faster, more intelligent hybrid AI models.
Emil Michael, the Under Secretary of War for Research and Engineering, details the radical technological transformation of the US military. He discusses the architecture and rapid launch of GenAI.mil, an internal AI platform powered by Gemini that reached over one million users in 30 days. He also outlines critical technology priorities, including scaled hypersonics and autonomous drone swarms, and the urgent need to rebuild the American defense industrial base for a new era of global competition.
Nikesh Arora, CEO of Palo Alto Networks, shares his unconventional journey and leadership philosophy. He provides a masterclass in building a multi-platform company through strategic M&A, explains why founders should sometimes ignore customers, and reveals how to lead with conviction while managing imposter syndrome.
Stewart Butterfield, co-founder of Slack and Flickr, shares the product frameworks and leadership principles that guided his success. He delves into concepts like "utility curves" for feature investment, the "owner's delusion" in product design, and why focusing on "comprehension" is often more important than reducing friction. He also introduces powerful mental models for organizational effectiveness, such as combating "hyper-realistic work-like activities" and applying Parkinson's Law to team growth.
Intuit CEO Sasan Goodarzi discusses the operational playbook for reinventing a 40-year-old company, from its slow transition to SaaS to its early adoption of AI. He shares insights on winning the SMB market by treating small businesses like consumers, building effective channel partnerships, and developing a platform strategy. Goodarzi also details his leadership philosophy, emphasizing that grit and curiosity are more critical than raw talent.
Co-founder Sam Ross discusses Numeral's journey from a personal e-commerce pain point to a venture-backed global tax platform. He covers the market opportunity created by outdated incumbents, the 'do things that don't scale' approach to finding product-market fit, lessons from fundraising, and how Numeral leverages AI to automate complex compliance workflows, shifting from a tool to a full-service solution.
MeshAgent introduces a multiplayer AI paradigm, shifting from single-user systems to collaborative 'Rooms' where teams of humans and agents can work together with shared context. This talk explores the platform's architecture, developer tools, and its approach to solving real-world collaborative tasks.
A deep dive into the architectural and economic foundations of memory for AI agents. The talk explores the core tradeoffs between classical data storage and dynamic agent behavior, introduces a human-inspired framework for memory, and discusses practical strategies and future directions for building reliable, evolving AI systems.
Jerry from LlamaIndex explains why naive Retrieval-Augmented Generation (RAG) fails in production and dives deep into advanced data quality techniques—from parsing complex documents and hierarchical indexing to chunking best practices—required to build robust, high-quality LLM applications.
Dell's Shirish Gupta and Ish Shah discuss the complexities developers face in leveraging on-device accelerators like NPUs and GPUs. They introduce Dell ProAI Studio, a solution designed to abstract away hardware-specific toolchains, enabling developers to easily run AI workloads locally for benefits like speed, cost, security, and offline capability.
Erik Torenberg, Patrick Hsu (Arc Institute), and Jorge Conde (a16z) discuss Arc's moonshot to create 'virtual cells' using foundation models to simulate biology. They cover why science is slow, how AI can accelerate drug discovery by predicting cellular perturbations, and the remaining bottlenecks in clinical trials and capital intensity that the biotech industry faces.
Get updates straight to your inbox. No spam, just useful content.