MWP – Artificial Intelligence Channel cover art

Artificial Intelligence

Episodes whose main subject is AI itself: building with, training, evaluating, or debating AI systems. AI used only as a tool for another topic goes to that topic.

1594 episodes Page 34 of 80 RSS Feed All feeds

#4316: How to Build Memory That Survives AI Sessions

Why AI agents forget between sessions — and how to fix it with markdown files instead of black-box memory.

context-and-memoryai-coding-assistantsprompt-engineeringworkflow-automationopen-source

#4314: The Hidden Layer Shaping Every AI Chat

Context windows are huge now, but relevance is the real bottleneck. How middleware decides what your AI actually sees.

context-and-memoryai-inferencemulti-agent-systemsrag

#4313: Did You Really Build That App? AI Imposter Syndrome

You built a working app with AI in a weekend. So why does it feel like you don't deserve to charge for it?

ai-coding-assistantsai-evaluationhallucinationscareers-and-hiringfuture-of-work

#4312: Why Speech-to-Text Still Fails at Its Own Name

When OpenAI's Whisper misheard its own name as "Wispr," it revealed why 95% word accuracy still isn't good enough.

speech-recognitionai-evaluationhallucinationscontext-and-memory

#4296: Auto-Splitting AI Threads: Smarter Context Management

How to build a system that automatically detects topic shifts and routes messages to the right thread.

context-and-memoryai-inferenceai-coding-assistantsworkflow-automation

#4274: Fixing Loop-Damaged Podcasts with AI and FFmpeg

Can an AI agent detect repeated audio, generate FFmpeg commands, and overwrite files in cloud storage without breaking RSS?

ai-coding-assistantsai-evaluationdevopscloud-computingopen-source

#4268: When AI Trains on AI: The Model Collapse Problem

What happens when AI trains only on AI-generated content? The answer is model collapse — and it's already happening.

training-datahallucinationsai-evaluationai-bias

#4208: The Awkward Honesty of AI Attribution

Why admitting AI helped feels like a confession — and what emerging norms actually work.

ai-evaluationai-alignmentopen-sourceai-coding-assistants

#4194: Custom GPTs: When to Build, When to Skip

A decision framework for knowing when a custom GPT is worth the overhead — and when to just open a fresh chat.

prompt-engineeringcontext-and-memoryai-coding-assistants

#4188: Find the Quietest Time to Drive Using Google's API

Query Google's Routes API to find statistically optimal driving times in Jerusalem — no gut feelings required.

cloud-computingdatabasesdata-storagecars-and-driving

#4180: Translation-Safe Writing for Global Supply Chains

How to write English that survives machine translation without losing critical specs.

translationai-evaluationhallucinationssupply-chainprocurement

#4170: Obfuscation as Risk Management with AI

How AI can protect whistleblowers and trauma survivors by intelligently obscuring identities while preserving story integrity.

ai-securityai-alignmentmulti-agent-systemsopen-source

#4169: Change Detection AI for Construction Sites

How AI catches what experts miss in construction site photos — from Siamese networks to transformer models.

computer-visiontransformer-architecturetraining-dataai-evaluation

#4167: Why AI Can’t Read Your Gmail (Yet)

Your AI misses emails and fails to send replies. It’s not dumb—the pipes are leaky.

model-context-protocolai-coding-assistantsworkflow-automationai-inference

#4157: Prompt Engineering Is a Misnomer — Managing Ambiguity in AI

Why the best AI outputs come not from tighter prompts, but from knowing where to leave room for surprise.

prompt-engineeringcontext-and-memoryspeech-recognitionai-evaluation

#4139: The Hosepipe-to-Digest AI: Your Outbox Middleware

An AI middleware that intercepts your outgoing emails, buffers them, and delivers a crisp executive summary.

workflow-automationai-coding-assistantsproductivitycontext-and-memory

#4106: Embedding Models vs LLMs: What Actually Connects?

Can you mix any embedding model with any LLM? And why are new embedding models still dropping if they're "solved"?

ragtraining-dataai-inferencecontext-and-memory

#4104: Why 20% of AI Scripts Loop on Themselves

Debugging the mysterious repetition bug affecting one in five podcast episodes.

ai-evaluationprompt-engineeringcontext-and-memoryai-inference

#4094: One Mind or Two? AI Podcast Dialogue Showdown

Can two AI agents create better podcast banter than one? We explore the tradeoffs.

multi-agent-systemsprompt-engineeringcontext-and-memoryai-evaluation

#4092: How AI Remembers What You Never Told It

How ChatGPT connected "wall anchors" to a power tool you bought days ago — without being asked.

context-and-memoryragai-inferenceprompt-engineering