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.
This talk introduces 'structured dissent,' a multi-agent orchestration pattern where believer, skeptic, and neutral agents debate decisions to overcome the 'confidently wrong' failure mode of single-agent LLM systems, improving reliability for high-stakes tasks like cybersecurity analysis.
A deep dive into the security vulnerabilities of Multi-Context Protocol (MCP) for AI agents. The talk explores how identity loss, "all-or-nothing" permissions, and disappearing audit trails create significant attack surfaces, and presents solutions like identity chain tracking, context-aware permissions, and intelligent auditing to secure agent-to-tool communication.
A detailed overview of a modular, five-agent system designed to combat the entire lifecycle of digital misinformation. Based on an ICWSM research paper, this practitioner's guide details the roles of the Classifier, Indexer, Extractor, Corrector, and Verifier agents. The system emphasizes scalability, explainability, and high precision, moving beyond the limitations of single-LLM solutions. The talk covers the complete blueprint, from agent coordination and MLOps to holistic evaluation and optimization strategies for production environments.
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.
Will Hang and Theophile Sautory from OpenAI provide a deep dive into Agent RFT, a powerful method for fine-tuning large language models to become more effective, tool-using agents. They explain how Agent RFT enables models to learn directly from their interactions with custom tools and reward signals, leading to significant improvements in performance, latency, and efficiency on specialized tasks. The session includes a detailed code demo, best practices, and success stories from companies like Cognition, Ambience, and Rogo.
Martin Keen explains the evolution of prompt engineering from an art to a software engineering discipline. He introduces LangChain and Prompt Declaration Language (PDL) as tools to manage the probabilistic nature of LLMs, ensuring reliable, structured JSON output through concepts like contracts, control loops, and observability.
Professor Andreas Zeller discusses his interactive 'Debugging Book,' arguing that systematic, automated debugging is a critical but neglected skill. He explores powerful techniques like delta debugging and automated repair, explaining how developers can build their own tools to make debugging a more plannable and efficient process.
Databricks’ Eric Peter and Corey Zumar introduce MLflow 3.0, focusing on its new "Agentic Insights" capabilities. They demonstrate how MLflow is evolving from providing tools for manual quality assurance in Generative AI to using intelligent agents to automatically find, diagnose, and prioritize issues, significantly speeding up the development lifecycle.
Adam D’Angelo (Quora/Poe) and Amjad Masad (Replit) debate the future of AI. They clash on whether LLMs are hitting limits, the timeline to AGI, and the societal impact of automating entry-level jobs while expert roles remain, potentially creating a "missing middle" in the workforce.
Experts analyze the 1X NEO humanoid robot's real-world viability and data challenges, delve into the complex copyright dispute between Japan's IP holders and OpenAI's Sora 2, and dissect the strategic implications of the new OpenAI and AWS partnership for AI infrastructure and multi-cloud strategies.
Get updates straight to your inbox. No spam, just useful content.