How Open Frontier Labs Actually Train Their Models
[2026 - Day 3 - Model Systems] Training a large language model is an exercise in tradeoffs you didn’t expect, where choices made for pre-training can shape post-training, agentic RL, and inference much later. Should you spend a week optimizing infrastructure and architecture, or just start training when every design choice affects rollout speed, memory use, and serving cost? This talk covers how to think about mdeol decisions: why architecture changes are rarely just about accuracy and almost always about performance, how inference choices determine what is feasible for post-training, and how frontier open labs design models for RL-heavy, agentic workloads. We’ll walk through the full lifecycle of a model, from pre-training to mid-training to post-training RL, examining how decisions at each stage shape the next and why tradeoffs around efficiency, capability, and inference cost rarely have clean answers SPEAKER: Sami Jaghouar - Head of Research, Prime Intellect 👉 Sign up for our "No BS" Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter ABOUT AI COUNCIL: AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools. FIND US: Website: https://aicouncil.com/ LinkedIn: / aicouncilconf X: https://x.com/aicouncilconf

The protocol that holds the internet together (ft. Amit Sahai)

Südkorea – Tschechien Highlights | Gruppe A, FIFA WM 2026 | sportstudio

Training Sand to Think: Artificial General Intelligence & Future of Physics

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Yann LeCun: World Models: Enabling the next AI revolution

Lessons From RL Systems That Looked Fine Until They Didn't

China's 1.4nm Breakthrough Terrifies America and Taiwan

Powering Agents with Context Graphs & Ontologies

Keynote: Linus Torvalds, Creator of Linux & Git with Dirk Hohndel, Founder, DH Consulting

But what is quantum computing? (Grover's Algorithm)

HW News - DRAM Companies Hit Trillions of Dollars, Bambu Open Source, NVIDIA Spark Concerns

RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source

Something is jamming GPS over Europe. Here's what we found

RLVR in Practice: From Synthetic Data to GRPO

6. Monte Carlo Simulation

Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup

This is not the AI we were promised | The Royal Society

Chip design from the bottom up – Reiner Pope

The most beautiful formula not enough people understand

