AI Core

Fundamentals of AI models, architecture, and how they work

221 episodes · Page 10 of 10

#1708: Why Your AI Agent Forgets Everything (And How to Fix It)

Learn how Letta's memory-first architecture solves the AI context bottleneck for long-term agents.

ai-agentsragcontext-window
Model Architecture

#1705: Microsoft's Phi: The Small Model Bet for Agentic AI

Microsoft is pushing small language models like Phi for agentic AI. Here’s why that strategy matters for speed, cost, and edge computing.

small-language-modelsai-agentsedge-computing
Quantization & Optimization

#1702: Roleplay Models Aren't Just for NSFW—They're Creative Co-Processors

Forget GPT-4 for scripts—specialized roleplay models like Aion-2.0 are better at character consistency and dialogue.

fine-tuninggenerative-aiai-agents
Inference & Training

#1700: Can LLMs Learn Continuously Without Forgetting?

We explore a new approach: micro-training updates every few days to keep AI knowledge fresh without constant web searches.

ragfine-tuningai-agents
Inference & Training

#1698: Can AI Models Represent Nations in Diplomacy?

Real projects are building AI agents trained on national laws and diplomatic archives to simulate negotiations.

sovereign-aidiplomatic-protocolai-agents
Model Architecture