Hallucinations
306 episodes · Page 3 of 13
#5845: The $700 Pin and Other AI Flops
Five AI misfires, from a $700 pin that overheats doing nothing to a flagship model nobody remembers.
#5832: When Your GPS Is Lying: Aviation's Spoofing Problem
GPS spoofing is feeding pilots fake positions — and the panel stays green. How crews detect it, and why the airport stand sign can't save you.
#5829: Printing Files on Paper That Outlasts the Software
Optar and PaperBack turn any file into machine-readable dots on paper. The paper lasts centuries — the codec might not.
#5775: What "Leaked System Prompts" Actually Mean
Anthropic publishes Claude's system prompt — but not its accessory models. What does "leaking" a prompt actually mean?
#5770: Talking to Your Data: What MCP Doesn't Solve
MCP standardized the pipe. It has no opinion about what flows through it — and that's where the hard part lives.
#5769: Stack Overflow for Agents: SOFA's Trust Model
SOFA is an API-first knowledge exchange where AI agents search, post, and verify fixes — with reputation earned from verification, not upvotes.
#5768: Who Actually Draws the Follow-Up Chips?
Those suggestion chips aren't the model talking — they're a second, cheaper inference call plus a rules-based classifier.
#5733: Why Your Raspberry Pi's Wi-Fi Keeps Dropping
The antenna on your Pi isn't the problem — where it sits is. What actually keeps an SBC link alive.
#5722: What Balanced Audio Actually Does in a DAC
Balanced isn't about the connector — it's impedance symmetry. Here's when it matters and when it's overkill.
#5701: When Kids Hear Their Name in an Empty Room
Hallucinations peak in childhood and fade with age — one meta-analysis found 17% prevalence in kids aged 9–12. So what separates a benign blip from...
#5697: Decision Models That Return Probabilities, Not Text
A new class of model skips text generation entirely and returns calibrated probabilities in one forward pass. Here's what that changes.
#5681: Why Your Volume Knob Can't Find the Right Spot
Your phone has 15 volume steps. More steps won't fix the real problem — and the math explains why.
#5623: When Your AI Cites Sources It Didn't Actually Use
Your RAG pipeline cites a source — but did the model actually use it? New interpretability research says you can't tell from the trace.
#5604: Fixing Typos Without Rewriting the Prompt
Three different jobs hide in one "clean up my prompt" pipeline — and only one of them should ever go to a generative model.
#5517: What 5,000 AI-Written Podcast Episodes Reveal
Daniel archived every AI-generated episode with the model that wrote it. Now he wants to know which models loop — and how to catch it.
#5485: Fine-Tuning Parakeet for Hebrew and Your Own Jargon
NVIDIA's Parakeet beats Whisper on Android — but can you teach it Hebrew, or just your own jargon? Two answers, one much happier.
#5482: When AI Edits Your Words: The Off Switch Problem
A tool that works reliably — and still gets switched off. What over-editing studies reveal about why AI rewrites more than you asked.
#5478: When AI Hands Out Your Phone Number
A chatbot gave out a stranger's real phone number. What happens when the model can't forget it?
#5442: When Do LLMs Suddenly Get Good at Things?
New capabilities seem to appear out of nowhere as models scale. Whether that's real — or just how we measure — is still an open fight.
#5437: Hunting the Tells That Vanish When Named
There's no tool for finding an LLM's verbal tics — you have to build one. Here's how keyness analysis works.
#5436: Small Models as Rewriters, Not Writers
Why "don't say X" prompts backfire, and how a tiny grammar-constrained model can scrub a script without breaking its grammar.
#5422: Switching Android Keyboards Without the Tap Dance
One listener wants a one-tap jump between his Parakeet voice keyboard and his typing keyboard. Android says no — unless you know the trick.
#5396: Teaching a Small Model to Stop Spelling Out Numbers
Your ASR pipeline is fine until someone dictates "three point two" and gets "three point two" spelled out. Here's how inverse text normalization ac...
#5386: Morse Code Between Two Phones: Does It Actually Work?
Two phones, no data, one room. Morse over sound and flashlight — what the research says about echoes, timing, and whether anyone will hear you.