AI Evaluation
516 episodes · Page 9 of 22
#4104: Why 20% of AI Scripts Loop on Themselves
Debugging the mysterious repetition bug affecting one in five podcast episodes.
#4094: One Mind or Two? AI Podcast Dialogue Showdown
Can two AI agents create better podcast banter than one? We explore the tradeoffs.
#4071: Four Tools for a Human Review Layer on AI Tags
Adding human review to AI-generated tags without building an admin panel from scratch.
#4059: LLM Councils for Post-Gallbladder Care
Can multiple AI models solve what no single doctor can? A deep dive into LLM councils for post-cholecystectomy syndrome.
#4057: How to Fix AI's Bullet Point Addiction
Why AI models default to bullet points and how textual LoRAs achieve 94% prose adherence.
#4056: How a $150 Geopolitical AI Simulation Scales to $15,000
One simulation run costs $150. To get meaningful results, you need 100 runs—that’s $15,000.
#4030: How ChatGPT Beat Affiliate Marketing and the Store Clerk
One man’s ChatGPT thread replaced affiliate clutter and floor staff. Can retailers catch up?
#3855: How One Trolley Exposed a Broken Review System
A 4.3-star rating hid dozens of identical complaints. Here's how reviews get gamed and what AI could do about it.
#3800: How AI Hallucinates Better Pixels: Upscaling Explained
The difference between interpolation and super-resolution, and why every upscaled image is a collaboration with training data.
#3767: How LLMs Actually Learn: Stages or Slurry?
Do large language models learn grammar first, then facts? The honest answer is messier and more fascinating.
#3713: How a Real PI Manages Thousands of Photos
Phone camera rolls don't cut it. Here's how real PIs organize, tag, and store thousands of evidence photos per month.
#3661: What 1000 AI Podcast Episodes Actually Prove
Scaling an AI podcast to 1000 episodes reveals what no 10-episode pilot can teach you about sustainability, cost, and habit formation.
#3596: Why an AI Model Kept Calling Itself Sonnet 4.6
When a Chinese model insists it's "Sonnet 4.6," is it theft, sloppy training, or something stranger?
#3553: Can AI Review Your Lease in Israel?
Can AI actually understand Israeli tenant law? We explore the tools, the gaps, and how to build your own.
#3515: Brain Scans Beyond fMRI: What Comes Next in Psychiatry
fMRI was a revolution — but it's no longer cutting edge. What new tools are emerging, and will they ever reach your clinic?
#3424: Catching Up on AI Without the Firehose
Four curated sources that filter AI noise into signal — Import AI, The Batch, Stanford HAI, and a podcast.
#3422: How Rival Labs Reverse-Engineer a New AI Model in Hours
Inside the organized frenzy when a closed-source model drops — and how competitors map its every weakness.
#3284: Agent Infrastructure Engineer: The New DevOps
Agentic AI is splintering into real engineering disciplines. Here's what the "DevOps of AI" actually does.
#3241: How to Write a Product Spec That Makes AI Find You the One
Stop typing three words into Google. The SPEC framework helps AI find exactly what you need.
#3171: How to Break an LLM's Bad Verbal Habits
Blacklists fail and regex inverts meaning. Here's what actually works to clean up AI writing tics.
#3170: Pharmacokinetics vs Neural Nets: Two Meanings of "Model
Two things called "models" that work completely differently — and why the confusion matters for patient safety.
#3157: Opus 4.8: What Actually Changed Under the Hood
Anthropic dropped Opus 4.8 with no fanfare. New training data, faster inference, and smarter refusals — here's what changed.
#3120: What Makes Agentic Search Tools Like Exa Actually Work?
Why swapping Google for Exa transformed our show's accuracy — and what agentic search does differently.
#3098: The Pilot with the Flashlight: Inside Aviation's Pre-Flight Walkaround
Why pilots still physically inspect planes before every flight — and what a 1979 crash taught us about trusting machines.