cost
71 talks
How to Actually Tokenmaxx and Save Millions
Tokens Are the Cheap Part
What Technical Due Diligence Finds When the Deck Says "70% Automated"
An AI Future Without the Lock-In
Every AI Company Is Accidentally Building a Bank
How I Learned to Stop Worrying and Love the Sandbox
Your LLM App Returned 200 OK. It Was Still Wrong.
Stop Rationing Tokens: Let the Harness Pick the Model
We Let Claude Code and Codex Race Human Researchers
Why LLM Recommenders Will Be AI's Biggest Consumer App
Operating Distributed Inference Systems at Scale
Where RL Will Take Search
Your Agreements Are a Database You Can't Query
Tokens Should Have Jobs
Mousepower: agents that can't be measured, can't be managed
Deep dive on LLM Inference at Scale
From Tokenmaxxing to Trusted Throughput
The Missing Layer in Agentic AI
FinOps for AI Agents: Who Spent All the Tokens?
Preferences Over Benchmarks: Model Routing
Computer-use models will agentify the web, not APIs
The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans
The Rise of CaaS: Context-as-a-Service for Agentic AI
Memory Harnesses for Long-Running Research Agents
Anthropic's CCA Exam as a Field-Guide for Agentic Engineering
Open Source Is Dead. Long Live Open Source.
The State of Model Routing
Notion's Token Town
The Biggest Challenge in Your Stack? Evals, Evals, Evals
Your LLM Stack Is a 2008 Database With Better Marketing
Stop Renting Your Cognitive Infrastructure
Stop Evaluating Models Like It's the 50s
Semantic Blindness: 500,000 Sensors Confused an LLM
Develop at Idea Velocity
We Cut 94% of AI Coding Tokens With a Local Code Index
Your Agent Is Wasting Tokens and You Don't Know It
What Lies Beneath the API
Rethinking What State-of-the-Art Means
How Google DeepMind Runs Agents at Scale
Scaling the Next Paradigm of Heterogeneous Intelligence
Feedback Loops are All You Need
Efficient Reinforcement Learning
Context Platform Engineering to Reduce Token Anxiety
The Unbearable Lightness of Agent Optimization
Hacking the Inference Pareto Frontier
Why We Don't Need More Data Centers
POC to PROD: Hard Lessons from 200+ Enterprise GenAI Deployments
What Every AI Engineer Needs to Know About GPUs
Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+DAU
Thinking Deeper in Gemini
Trends Across the AI Frontier
Analyzing 10,000 Sales Calls With AI In 2 Weeks
Effective AI Agents Need Data Flywheels, Not The Next Biggest LLM
Real AI Agents Need Planning, Not Just Prompting
Frontier Feud
Building and evaluating AI Agents
Anthropic in the Enterprise
Finetuning: 500M AI Agents in Production with 2 Engineers
Rethinking how we Scaffold AI Agents
Agent Evals: Finally, With The Map
Lessons from building GenAI based applications
The Price of Intelligence - AI Agent Pricing in 2025
Giving a Voice to AI Agents
The GenAI Maturity Curve, or You Probably Don't Need Fine Tuning
How to Evaluate a Model for Your Use Case
No-code fine-tuning
Scaling AI in Education: A Khanmigo Case Study
Mastering LLM Inference Optimization From Theory to Cost Effective Deployment
AI Frontiers in Trust and Safety: Combatting Multifaceted Harm on Tinder at Scale
GPT Web App Generator: 10,000 Apps Created in a Month
Domain adaptation and fine-tuning for domain-specific LLMs