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 26 of 80 RSS Feed All feeds

#5390: Chaining Small Models for Dictation Cleanup

Daniel's Android dictation fork won't render "three point five" as a decimal. How many models does cleanup actually need?

local-aispeech-recognitionworkflow-automationai-inferenceopen-source

#5389: Hugging Face vs Kaggle: Where Models Actually Live

Hugging Face and Kaggle aren't rivals — one is infrastructure, one is a practice field. Here's how the two platforms actually differ.

training-dataopen-sourcelocal-aiworkflow-automation

#5384: Android ASR Runtimes: LiteRT, ExecuTorch, and Why Your Phone Has No VRAM

Why does your phone have no VRAM number? A tour of Android's runtime layer and what it takes to run ASR locally.

speech-recognitionlocal-aiai-inferencegpushallucinations

#5355: Why AI Emails Don't Sound Like You

ChatGPT's Gmail integration can now send email for you. The hard part is making it sound like you — not a committee-written average.

prompt-engineeringcontext-and-memoryai-alignmentworkflow-automationreasoning-models

#5318: Rebuilding the Dremel 4250 Manual for One Task

A 48-page Dremel manual, filtered down to only what you need to engrave four-digit inventory codes.

prompt-engineeringai-coding-assistantspower-toolsengravingproduct-durability

#5313: System Prompt Order Is Load-Bearing

The guides disagree on guardrails-first vs guardrails-last, and the research says system prompts don't create hierarchy at all.

prompt-engineeringai-alignmentmulti-agent-systemsreasoning-models

#5312: Fighting Fake-Personalized Spam With AI Sinkholes

Scraped flattery, fake familiarity, and the one-sided ask — plus the tarpit history behind Daniel's sinkhole agent idea.

ai-securitymulti-agent-systemsai-evaluationworkflow-automation

#5301: Why Talking Robots Are Really a Committee

That humanoid chatting while it moves? It's not one brain — it's a stack of separate models glued together.

multi-agent-systemsai-inferencegpusmodel-context-protocolopen-source

#5300: When the Interviewer Isn't Real

AI avatars are already interviewing job candidates — often without saying so. The disclosure toggle ships off by default.

ai-alignmentai-biasdeepfakescareers-and-hiringworkplace-culture

#5278: Photogrammetry vs Gaussian Splat: Scanning a Room Without LiDAR

No LiDAR? No problem. How capture modes, masking, and vertical parallax shape a phone-based room scan.

computer-visionmaterials-sciencehome-inventorygpus

#5277: AI Handles the GTD Inbox So You Don't Have To

GTD says capture everything — then caps your inbox at 100 items. What if AI did the organizing layer instead?

productivityworkflow-automationai-coding-assistants

#5262: How the Talmud Outlived Every Book Burning

From the 1242 Paris burning to Sefaria's AI agents, the chain of transmission was never in the books — it was in the network.

ragmodel-context-protocolarchaeologyhebrew-biblejewish-history

#5256: Ruby Won the AI Benchmark. Is It Dying Anyway?

97% of public Ruby repos sat untouched for six months — yet Ruby beat Python in an AI coding benchmark. What's actually declining?

ai-coding-assistantsai-evaluationprogramming-languagesopen-sourcetraining-data

#5255: When AI Writes the Code, Who Checks It?

If agents write the code, the human job becomes knowing when it's wrong. What that means for languages, jobs, and CS degrees.

ai-coding-assistantsai-evaluationprogramming-languagesfuture-of-workai-alignment

#5251: Recovering the Moon That's Already in the Pixels

Image restoration clarifies photos without inventing detail — until the fidelity dial shows up. Here's what's in the toolbox.

ai-evaluationhallucinationsgenerative-mediacomputer-visionopen-source

#5245: Training a Model on 100 Phone Photos

One drawer of screws, a hundred phone photos, and a schema. When does a small custom model beat a fine-tuned VLM?

training-datafine-tuningcomputer-visionlocal-ai

#5230: Why Your Research Agent Won't Stop Searching

Most agent search runs add no new evidence — and 66-85% of the context window is just search snippets. Here's what actually stops the loop.

multi-agent-systemsai-evaluationragai-inferencereasoning-models

#5198: Counting the AI Models Nobody Releases

YOLO is free — the labeled data isn't. Why the custom image models that matter most are the ones you'll never see on Hugging Face.

computer-visiontraining-dataopen-sourceintellectual-property

#5188: DeepSeek's Point Release That Isn't

DeepSeek shipped a whole new architecture and called it a point release. Here's what actually changed inside the model.

transformer-architectureai-inferencelocal-aicontext-and-memoryreasoning-models

#5187: Translation Is Not a Pipe: What Machines Miss

Rubrics rate machine translation above human work — until readers pick side-by-side. What translators know that metrics can't see.

ai-evaluationtraining-dataai-biasspeech-recognition