AI

Artificial intelligence, machine learning, and everything LLM

871 episodes Page 3 of 44

#2664: Can You Trust an LLM's Raw Knowledge?

Why pre-trained knowledge isn't reliable for facts — and what actually makes models useful.

large-language-modelsfine-tuningrag

#2657: How Background Removal Actually Works (and Why It Matters for AI Art)

Background removal isn't magic — it's multiple AI systems working in sequence. Here's what's actually happening under the hood.

image-generationcomputer-visiongenerative-ai

#2653: Puppetry in America: From Vaudeville to Muppets

Tracing the surprising institutional depth of American puppetry, from UConn's puppet arts program to the Henson revolution.

puppetryamerican-theaterarts-funding

#2651: AI Training Itself: Student, Teacher, and Grader

Can models generate their own training data and judge their own outputs? The promise and pitfalls of fully AI-led pipelines.

large-language-modelsai-trainingmodel-collapse

#2650: How to Catch an LLM's Bad Writing Habits

A practical guide to analyzing podcast transcripts for repetitive language and dialogue patterns — from Python word counts to embedding clustering.

large-language-modelsprompt-engineeringfine-tuning

#2649: Freelancing Without Getting Burned: Clients, Contracts & Cash Flow

How many clients do you need to survive? And what contract clauses actually protect you?

scope-creepclient-managementfreelancing

#2647: Async Communication: Tools, Norms, and AI Mediation

How to choose the right async tool, set boundaries with clients, and where AI fits in.

remote-workproductivitywork-culture

#2645: How to Document Failures for Your AI Second Brain

Stop writing diary entries. Start writing retrospectives your AI agent can actually use.

knowledge-managementpersonalized-aivector-databases

#2644: Crafting Agendas That Actually Work (With AI)

Stop writing table-of-contents agendas. Learn the diplomat’s method for crafting meetings that actually achieve their goals.

productivityconversational-aiprofessional-communication

#2643: How Stenographers Type 300 Words Per Minute

Court reporters don’t type letters—they chord syllables at 300 words per minute. Here’s how it works and why AI can’t replace them yet.

speech-recognitionaudio-processingaccessibility

#2641: Whiteboard to Clean Diagram with Nano Banana

How Nano Banana finally solves the text rendering problem, turning messy whiteboard photos into polished tech diagrams.

image-generationcustom-asrai-ethics

#2640: Batch Inference Use Cases and Instructional AI in 2026

Beyond cheaper tokens—how batch inference changes AI workflows and why instructional models beat conversational ones for automated jobs.

llm-as-a-judgebatch-inferenceinstruction-following

#2639: How Re-Ranking Actually Works in Search and RAG Pipelines

Why your search results miss the mark — and how cross-encoders fix it.

ragsearchinformation-retrieval

#2638: How to Build Disposable AI Agents at Runtime

Create ephemeral AI agents that answer questions about specific items, then vanish. No persistent configuration needed.

ai-agentscontext-windowrag

#2636: Take Notes Like a Diplomat

What WikiLeaks cables teach us about capturing meetings: judgment over transcription, context over completeness.

diplomatic-protocolprofessional-communicationmetadata-analysis

#2634: Mining Latent Value from AI Prompts

How to extract durable personal context from raw prompts and build a self-healing memory layer for AI systems.

ai-memorycontext-windowprompt-engineering

#2632: How to Start a Meetup Without Burning Out

Practical steps for launching a local community around any interest — without it taking over your life.

productivitymeetup-logisticscold-start-problem

#2622: How Transformers Actually Work: Attention, Tokens, and Context

How one architectural change unlocked chatbots, image generation, and protein folding — explained without the jargon.

transformerslarge-language-modelsgpu-acceleration

#2604: Self-Hosted Screen Recording: Tools Beyond Loom

Practical tools and trade-offs for async video documentation with real data control across platforms including Linux.

open-sourceprivacyscreen-recording

#2603: Building Agent Skills for Creative Workflows

How composable AI agent skills turn tedious media tasks into one-instruction operations for creatives.

audio-engineeringautomationcreative-workflows