reinforcement-learning
80 talks
Small Models, Big Results: Training a Finance Agent for Under $500
Your LLM Judge Is a Confident Liar: Building Better Verifiers
Beating RL With Reflection: GEPA and Optimize Anything
Where RL Will Take Search
Einstein Arena: Harnessing Collective Agent Intelligence for Open Science
Training Krea 2: What Matters in Generative Model Training
From RL to IRL
Scaling Compute on Context
Scaling up Continual Learning
Taking Reinforcement Learning Cross Datacenter
Teaching AI to Find Real Vulnerabilities
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It
Data and Environment Curation for Post-Training LLMs
Ending AI Slop
Learning on the Job: The Future of Post-Training
Reinforcement Learning without Verifiable Rewards
Scaling to Long Horizons
The Base Model Is Dead
The Data for Fully Autonomous Software Engineers and Companies
What's Next After RLHF?
First Steps Toward Automated AI Research
Morgan Stanley's ALPHALAB: Multi-Agent Research Across Optimization Domains
Why Off-the-Shelf AI Doesn't Understand Money
AI tools for Forward Deployed Engineering
State of Data
Everything Is a Rollout
Vending-Bench: Long-Horizon Agent Evals
Stop Burning Tokens: Why Self-Improvement Needs Domain Expertise First
Special Topics in Kernels, RL, Reward Hacking in Agents
Computer-Use 2.0: Agents Just Got Multi-Cursor
Recursive Model Improvement
Modern Post-Training: A Deep Dive
How We Taught Agents to Use Good Retrieval
Stop Making Models Bigger, Make Them Behave
Task Fidelity Scaling Laws
What Lies Beneath the API
Lessons from Trillion Token Deployments at Fortune 500s
Everything I Learned Training Frontier Small Models
What Do Models Still Suck At?
Judge the Judge: Building LLM Evaluators That Actually Work with GEPA
Let LLMs Wander: Engineering RL Environments
AGI: The Path Forward
The Unreasonable Effectiveness of Prompt Learning
Code World Model: Building World Models for Computation
Minimax M2: Building the #1 Open Model
Hard Won Lessons from Building Effective AI Coding Agents
Agent Reinforcement Fine-Tuning
Efficient Reinforcement Learning
RL Environments at Scale
Building Cursor Composer
Agents are Robots Too: What Self-Driving Taught Me About Building Agents
Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL
Z.ai GLM 4.6: What We Learned From 100 Million Open Source Downloads
AI Engineer Code Summit 2025
Fuzzing in the GenAI Era
Useful General Intelligence
Infrastructure for the Singularity
Building Metrics that Actually Work
What Is a Humanoid Foundation Model? An Introduction to GR00T N1
Latent Space Paper Club: AIEWF Special Edition (Test of Time, DeepSeek R1/V3)
Stateful environments for vertical agents
A Taxonomy for Next-gen Reasoning
How to Train Your Agent: Building Reliable Agents with RL
Reinforcement Learning, Kernels, Reasoning, Quantization & Agents
Measuring AGI: Interactive Reasoning Benchmarks for ARC-AGI-3
RL for Autonomous Coding
Benchmarks Are Memes: How What We Measure Shapes AI and Us
Thinking Deeper in Gemini
Training Agentic Reasoners
New York Times' Connections: A Case Study on NLP in Word Games
Your Personal Open-Source Humanoid Robot for $8,999
RFT, DPO, SFT: Fine-tuning with OpenAI
Reasoning + RL
Will Agent Evaluation via MCP Stabilize Agent Networks?
Creating Agents that Co-Create
AI Engineering at Jane Street
Reinforcement Learning for Agents
How to Improve Your Agents: Academic Lit Review
Agent Engineering (Day 2)
Which Jobs Can Be Replaced Today