Tokenless

Llm training

Why a Nation Can't Outsource Its Frontier AI - Alistair Pullen (Cosine AI)

Why a Nation Can't Outsource Its Frontier AI - Alistair Pullen (Cosine AI)

Alistair Pullen, CEO of Cosine, discusses the UK's sovereign AI initiative, born from US export controls. He outlines Cosine's unique economic model, competing with "millions" against "billions" by licensing models instead of hosting inference. Pullen delves into why open models lag frontier systems, emphasizing active parameters and post-training data. He explains Cosine's innovative approach to "slop" through process-based RL and credit attribution, advocating for runtime proof in code review. The conversation covers their hierarchical "Swarm" sub-agent system, the challenges of memory, and advanced synthetic data generation, concluding on the geopolitical impact of export controls as an unexpected catalyst for UK AI.

The Prime Intellect Stack — Will Brown, Prime Intellect

The Prime Intellect Stack — Will Brown, Prime Intellect

Deep dive into Prime Intellect's open-source ecosystem for post-training LLMs, covering the modular Verifiers V1 environment design, the asynchronous and scalable Primer RL training framework, and the Lab platform for hosted training and fine-tuning. Learn about advanced reward systems, the interception server pattern, and tokenization control with the Renderers library, all designed to enable frontier agentic model development.

Efficient Reinforcement Learning – Rhythm Garg & Linden Li, Applied Compute

Efficient Reinforcement Learning – Rhythm Garg & Linden Li, Applied Compute

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.

Zai GLM 4.6: What We Learned From 100 Million Open Source Downloads — Yuxuan Zhang, Z.ai

Zai GLM 4.6: What We Learned From 100 Million Open Source Downloads — Yuxuan Zhang, Z.ai

Zhang Yuxuan from Z.ai details the technical roadmap behind the GLM-4.6 model series, which has achieved top performance on the LMSYS Chatbot Arena. The summary covers their 15T token data recipe, the SLIME framework for efficient agent RL, key lessons in single-stage long-context training, and the architecture of the multimodal GLM-4.5V model.

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Guanhua Wang from Microsoft's DeepSpeed team explains ZeRO++, a system that tackles the communication bottleneck in large-scale LLM training. By quantizing weights and gradients, ZeRO++ reduces communication volume by 4x, leading to training speedups of over 2x, particularly in low-bandwidth and small-batch-size environments.

The Startup Powering The Data Behind AGI

The Startup Powering The Data Behind AGI

Edwin Chen, founder and CEO of Surge AI, shares the company's origin story, its rapid, bootstrapped growth, and its research-driven philosophy on data. He critiques traditional data labeling, explains why metrics like inter-annotator agreement fail for complex tasks, and offers a sharp analysis of benchmark hacking. Chen also details the future of data, from multimodal and agentic reasoning in rich RL environments to the need for hyper-specialized expertise for scientific discovery.

Next →