continual-learning
36 talks
How do you diffuse AI into the real world?
Your Agent Evolved. Your Evals Didn't.
Beyond Static Intelligence: Evaluating Continual Learning
Bringing Continual Learning into Enterprises
Gradient-Free Continual Learning
Improving Agents is a Data Mining Problem
Intelligence + Continual Learning = Expertise
Lessons from Studying Every Memory System
Scaling Compute on Context
Scaling up Continual Learning
Local Models: Trust, Control, Optimization
Learning on the Job: The Future of Post-Training
The Base Model Is Dead
Wearing the Agent: From Group Chats to Glasses
Building Closed-Loop Evals for a Multimodal Agent at Scale
Learned Execution Graphs for Anomaly Detection & Drift in APIs
The Unreasonable Effectiveness of Separating the Task from the Model
Active Graph Agent Runtime (BabyAGI 4)
Why Your Agent Disagrees With Itself (And What To Do About It)
Stop Burning Tokens: Why Self-Improvement Needs Domain Expertise First
On AI and Knowledge
Build AI Systems for Discernment, Not Approval
Continual Learning for AI Agents: From Failures to Durable Improvements
AI-Driven Multi-Document Correlation for Financial Compliance
User Signal Dies at the Retrieval Boundary
How Lovable self-improves every hour
Malleable Evals: Why Are We Evaluating Adaptive Systems with Static Tests?
Agent Optimization with Pydantic AI: GEPA, Evals, Feedback Loops
Building your own software factory
Don't Build Agents, Build Skills Instead
Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL
Turning Fails into Features: Zapier's Hard-Won Eval Lessons
"Data readiness" is a Myth: Reliable AI with an Agentic Semantic Layer
Effective AI Agents Need Data Flywheels, Not The Next Biggest LLM
Your Evals Are Meaningless (And Here's How to Fix Them)
Training Albatross, An Expert Finance LLM