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.
Robert from OpenAI discusses the critical role of structured evaluations (evals) and graders for developing advanced collaborative agents. He explores the limitations of 'vibe-based' assessments, introduces a maturity model for evals, and presents a comprehensive rubric for measuring agent performance beyond simple accuracy, connecting these concepts to the power of Reinforcement Fine-Tuning (RFT).
Karan Goel, CEO of Cartesia, discusses the fundamental limitations of Transformer architectures, arguing they behave more like retrieval systems than learning systems. He explains how State Space Models (SSMs) enable compression and abstraction, and why Cartesia is tackling multimodal intelligence by first solving for voice AI, aiming to develop a transferable 'recipe' for end-to-end representation learning.
Spec-Driven Development offers a structured, reproducible, and reliable alternative to 'vibe coding' in the AI era. Al Harris from the Kiro team explains how to leverage specs as living documentation, integrate external tools via MCPs, and use property-based testing to create a tight feedback loop from natural language requirements to verified code.
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.
![The Mathematical Foundations of Intelligence [Professor Yi Ma]](https://img.youtube.com/vi/QWidx8cYVRs/maxresdefault.jpg)
Professor Yi Ma presents a unified mathematical theory of intelligence built on two principles: parsimony and self-consistency. He challenges the notion that large language models (LLMs) understand, arguing they are sophisticated memorization systems, and demonstrates how architectures like the Transformer can be derived from the first principle of compression.
Professor Yi Ma presents a unified mathematical theory of intelligence based on two principles: Parsimony and Self-Consistency. He argues that current AI, particularly LLMs, excels at memorization by compressing already-compressed human knowledge (text), but fails at true abstraction and understanding. His framework, centered on maximizing the coding rate reduction of data, provides a first-principles derivation for architectures like Transformers (CRATE) and explains phenomena like the effectiveness of gradient descent through the concept of benign non-convex landscapes.
Shane Legg, Chief AGI Scientist at Google DeepMind, outlines his framework for AGI, predicting 'minimal AGI' within years and 'full AGI' within a decade. He details a path to more reliable systems and introduces 'System 2 Safety' for building ethical AI. Legg issues an urgent call for society to prepare for the massive economic and structural transformations that advanced AI will inevitably bring.
Shane Legg, Chief AGI Scientist at Google DeepMind, outlines his framework for AGI levels, predicts a 50% chance of minimal AGI by 2028, and discusses the profound societal and economic transformations that will follow.
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 deep dive into the challenges and solutions for efficient Reinforcement Learning (RL) in enterprise settings. The talk contrasts synchronous and asynchronous RL, explains the critical trade-off of "staleness" versus stability, and details a first-principles system model used to optimize GPU allocation for maximum throughput.
Get updates straight to your inbox. No spam, just useful content.