Context and Memory
299 episodes · Page 3 of 13
#4786: Markdown vs Vectors for Agent Memory
Why coding agents need two kinds of memory — and why mixing them creates a sync nightmare.
#4774: When a Token Isn't a Word Anymore
Images, audio, and code all use "tokens" — but they're completely different things. Here's how tokenization actually works across modalities.
#4760: Context Window Management: Cutoff vs. Compaction
Trailing cutoff or auto-compaction? How to manage Claude Code's context window without losing critical information.
#4751: AI Agents vs Anti-Bot Systems
Why AI agents get blocked by anti-bot systems and what actually works to get through.
#4720: Compass vs. Warning Sign: Prompting for Long-Term AI
How positive and negative instructions reshape AI behavior differently — and why "preserve this" beats "fix this" in system prompts.
#4701: Why Claude Code Re-Introduces Itself to Your Repo
Claude Code remembers your preferences but not your codebase. We explore why that's by design and how to work around it.
#4699: The Hidden Engine: What Makes Claude Code Tick
Is it the model or the harness? We break down the invisible scaffolding that turns LLMs into real agents.
#4696: Why AI Over-Explains Simple Tasks
Why does AI turn a simple request into a 24-page document? We explore the training biases and architectural limits behind AI's tendency to over-del...
#4686: How Claude Code's Patience Works: Fork, Wait, and the Transcript Stack
Claude Code's "waiting" is an illusion. We break down the Unix primitives behind its background task system and where the analogy cracks.
#4682: When Context Windows Grow: What Survives?
If context windows jump to 10M tokens, which AI engineering practices survive? We separate load-bearing architecture from temporary scaffolding.
#4648: Graph Engineering: AI Memory Beyond Retrieval
How linked notes and knowledge graphs are turning AI agents from memory tools into discovery engines.
#4619: The Token Trap: Why AI Context Windows Confuse Everyone
Token counts are everywhere, but they don't tell you what AI can actually do. Here's what should replace them.
#4604: When Sub-Agents Overwhelm the Orchestrator
Daniel's inventory system hit a wall when parallel sub-agents flooded the orchestrator's context window. We break down the math and the fix.
#4588: The Hidden Cost of Conversational AI: Why Stateless LLM Calls Matter
Why conversational AI tools are making batch document processing slower, costlier, and less reliable — and what to do about it.
#4586: Fixing Stale UI: The 4-Link Chain of Data Flow
Why does a number on screen stay frozen after an upload? We trace the 4-link chain from response to redraw — and where it breaks.
#4584: Directing Context Loss: Smart Compaction Prompts
Learn how to steer Claude Code's context compaction with targeted instructions — turning a lossy default into a directed operation.
#4531: Grandpa Mode: A 37-Year-Old's Guide to Premature Nostalgia
Daniel's back injury becomes the launchpad for a comedic "old time grandpa" persona — here's the playbook for doing it right.
#4523: Can You Trust an AI's Summary?
Dedicated text compressors exist but aren't in production. The real problem? Nobody can verify the summary didn't drop what mattered.
#4497: Voice-First Stack Consolidation
Two transcription apps, two text expanders, no sync — and snippets about to fight each other. The path forward.
#4492: What Makes a Container Robot-Ready?
The hidden specs that turn a plastic box into something a robot can pick, read, and move at industrial speed.
#4458: How Headroom Compresses Agent Context Without Breaking Outputs
A deep dive into Headroom's content-aware compression pipeline that promises 20-95% token savings without changing agent answers.
#4457: OpenViking: A Filesystem for AI Agent Memory
OpenViking unifies memory, RAG, and skills into a browsable filesystem for AI agents — no vector database abstraction needed.
#4445: AI Agents Keep Undoing Each Other's Work
Why AI coding agents silently revert each other's fixes — and three memory strategies that prevent it.
#4374: How AI Agents Finally Made the Terminal Accessible
How Claude Code removes the memory tax that kept neurodivergent users from living in the terminal.