open-models
60 talks
I Spent Two Years Building the Median
Research to Reality with Google DeepMind
What Makes Open Models Fast in Production
GLM-5.2: Open Weights, Near-Frontier Intelligence
Teaching LLMs to Speak Spotify
Large clusters for small models
The Frontier AI Inference Cloud for Agents
Why AI Agents Need Million-Token Context
Local Models: Trust, Control, Optimization
Open Source Is Dead. Long Live Open Source.
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It
Scaling to Long Horizons
Training Frontier Models to Out-Think Hackers
The Desktop Frontier
From Tokens to Cells: Foundation Models for Single-Cell Biology
The AI bugpocalypse is here. Now what?
State of the Union: Why Local, Why Now
Sovereign Escape Velocity: Ownership with Open Models
Text Diffusion
Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning
Why TTS Models Now Look Like LLMs
FLUX, Open Research, and the Future of Visual AI
Training an LLM from Scratch, Locally
Everything I Learned Training Frontier Small Models
Gemma 4 Deep Dive
Gemma, DeepMind's Family of Open Models
Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX
Minimax M2: Building the #1 Open Model
Z.ai GLM 4.6: What We Learned From 100 Million Open Source Downloads
AI Engineer Paris 2025, Day 2
Robotics: why now?
The Rise of Open Models in the Enterprise
Using OSS Models to Build AI Apps with Millions of Users
How LLMs Work for Web Devs: GPT in 600 Lines of Vanilla JS
The Wild World of AI: 6 Months That Changed Everything
2025 in LLMs so far, illustrated by Pelicans on Bicycles
Trends Across the AI Frontier
New York Times' Connections: A Case Study on NLP in Word Games
Building Agentic Applications with Heroku Managed Inference and Agents
How fast are LLM inference engines anyway?
The Future of Qwen: A Generalist Agent Model
Personal, Local, Private AI Agents
WTF do people use Open Models for?
Customized, production-ready inference with open source models
Unveiling the Latest Gemma Model Advancements
LLM Quality Optimization Bootcamp
Accelerate your AI journey with Azure AI model catalog
Decoding Mistral AI's Large Language Models
Moondream: How Does a Tiny Vision Model Slap So Hard?
Making Open Models 10x Faster and Better for Modern Application Innovation
Everything You Need to Know About Fine-tuning and Merging LLMs
Building State of the Art Open Weights Tool Use: The Command R Family
Low Level Technicals of LLMs
Open Challenges for AI Engineering
GPUs & Inference Track
Open Models track
Open Questions for AI Engineering
Harnessing the Power of LLMs Locally
AI Engineering 201: Inference
Building AI For All