#context-window
18 episodes
#2205: When AI Coding Agents Forget: Five Approaches to Context Rot
As coding agents handle longer sessions, they accumulate noise and lose crucial information. Five competing frameworks are solving this differently...
#2164: Getting the Most From Large Context Windows
Frontier models have million-token context windows, but attention degrades well before you hit the limit. New research reveals why bigger isn't bet...
#2062: How Transformers Learn Word Order: From Sine Waves to RoPE
Transformers can’t see word order by default. Here’s how positional encoding fixes that—from sine waves to RoPE and massive context windows.
#2057: How Agents Break Through the LLM Output Ceiling
The output window is the new bottleneck: why massive context doesn't solve long-form generation.
#2005: Why Your GPU Changes LLM Output
Running the same LLM on different GPUs can produce different results. Here’s why that happens and how to test for it.
#1913: AI Context Windows Are Junk Drawers
Stop paying for old messages. Here's how to keep your AI sessions clean and on-topic.
#1856: Two AIs Chatting Forever: Why They Go Crazy
What happens when two ChatGPT instances talk forever? They hit a politeness loop, forget their purpose, and spiral into gibberish.
#1828: Mastering 2M Token Context in Agentic Pipelines
A massive context window sounds like a dream, but it can quickly become a nightmare for complex AI workflows.
#1811: Stop Hardcoding User Names in AI Prompts
Three methods for storing user identity in AI agents—and why the "Fat System Prompt" breaks production apps.
#1718: The Ralph Wiggum Technique: AI That Codes Itself
Stop babysitting AI agents. Learn the Ralph Wiggum technique to automate iterative coding loops and let AI finish the job itself.
#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.
#1629: Why Your AI Agent Needs Loops: A Deep Dive into LangGraph
Stop building linear chains and start building cycles to create agents that can reason, self-correct, and maintain complex state.
#1573: Weird AI Experiment: AI Supremacy Debate
Claude and Gemini go head-to-head in a heated debate over speed, reasoning, and who really owns the future of AI.
#1498: The Multi-Player Shift: Sharing One AI Brain
Stop copy-pasting prompts. Explore how shared "multi-player" AI is turning solitary chatbots into collaborative team members.
#917: Agent Mirror Organizations: Scaling AI Memory and Logic
Herman and Corn dive into Cloud Code and nested AI agents. Can "agent mirror organizations" solve the context window crisis?
#795: From Chat to Do: The Power of Sub-Agent Delegation
Explore the shift from simple chatbots to agentic swarms and how sub-agent delegation is solving the problem of context degradation.
#133: Quantum AI: The End of Brute Force Computing
Discover how quantum computing is transforming AI from brute-force scaling to surgical precision in this deep dive into the 2026 tech landscape.
#126: The Spotlight Effect: Understanding AI Attention Mechanisms
Why do AI models "lose the plot" after a few thousand words? Discover the mechanics of attention and the innovations solving context window limits.