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.
A panel of university students from LSE, Princeton, Berkeley, and ASU discuss the real-world impact of AI on campus life. They cover how AI is used as both a powerful learning tool and a crutch, the innovative projects students are building, how universities are adapting, and the challenges of navigating cheating, job applications, and 'AI slop' in a rapidly changing educational landscape.
Explore how Temporal, a durable execution framework, brings resilience and scalability to AI agents built with the OpenAI Agents SDK. This summary covers Temporal's core concepts of Workflows and Activities, the official integration that makes OpenAI agents durable, and patterns for orchestrating multiple micro-agents.
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.
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.
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.
Waymo Distinguished Engineer Vincent Vanhoucke discusses the core challenges of autonomous driving, explaining how Waymo fuses data from cameras, LiDAR, and radar to build a robust perception system. He delves into the "closed-loop" problem, the critical role of generative AI and simulation in training and validation, and how modern multimodal models are used in a teacher-student framework to distill vast world knowledge into the vehicle's onboard system, aiming for a safety standard that surpasses human performance.
Giga co-founders Varun and Esha discuss their product-first approach to enterprise AI, detailing their innovative 'AI Forward-Deployed Engineer' model that enables rapid, scalable customer support automation. They break down how they solve complex, multi-party use cases for clients like DoorDash and share their vision for expanding beyond support to become a comprehensive ops automation platform.
Priscilla Chan and Mark Zuckerberg of the Chan Zuckerberg Initiative (CZI) discuss their strategy to accelerate scientific discovery through the Biohub, an operating philanthropy at the intersection of frontier AI and biology. They detail the development of foundational tools like the Cell Atlas, a 'periodic table for biology,' and their new focus on building virtual cell models to allow scientists to test high-risk hypotheses in silico, ultimately aiming to cure, prevent, and manage all diseases.
The OpenAI Sora team discusses the technology behind their video generation model, from the diffusion transformers and space-time tokens that enable object permanence to their vision for Sora as a world simulator capable of scientific discovery. They also cover their product philosophy, which prioritizes creative inspiration over mindless consumption, and their strategy for building a new creator economy with IP holders.
Get updates straight to your inbox. No spam, just useful content.