
Advertise on podcast: Linear Digressions
Rating
4.8from
Categories
This podcast has
332 episodes
Language
EnglishPublisher
Katie MaloneExplicit
No
Date created
2014/11/13
Latest episode
2026/11/09
Average duration
26 min.
Release period
8 days
Description
Demystifying AI for the intelligently curious
Unlock Linear Digressions podcast Email contact info,
Listeners & Audience details
Email contact information
Direct podcast contact details

Listeners
Audience numbers & engagement insights

Audience details
Podcast Insights

Podcast episodes
Check latest episodes from Linear Digressions podcast
GPU Architecture for LLM Inference: Memory, Bandwidth and Hardware Explained
2026/11/09
GPUs are the engines powering every AI conversation you've ever had — but what's actually happening inside those chips when an LLM generates a response? Understanding GPU fundamentals turns out to be surprisingly useful for making sense of why inference works the way it does, from the prefill stage that processes your entire prompt at once to the serial decode step that produces tokens one by one. If you want to understand the real constraints shaping modern AI systems, this is where to start.
KV Cache Fundamentals
2026/11/02
The unsung hero of every LLM conversation you've ever had? A clever optimization called the KV cache. Self-attention is computationally brutal — every token attending to every other token means costs that scale as N², and that blowup gets worse with every turn of a conversation. The KV cache is what keeps that from becoming completely intractable at scale. Today's episode goes deep on how it works, why inference is a harder and more interesting problem than it gets credit for, and what's really happening under the hood when you chat with an LLM.
AI Inference 101
2026/10/26
Everyone talks about training the model — the data, the compute, the alignment magic. But what happens after the weights are frozen and millions of users start hammering it with prompts? That's inference, and it's a surprisingly deep rabbit hole of engineering challenges that rarely gets the spotlight it deserves. This week I kick off a new series unpacking the full inference ecosystem — from the moment a model completes training to the moment tokens land in your hands.
Back Next Week
2026/10/19
Back Next Week by Katie Malone
Back in Two Weeks
2026/10/12
Back in Two Weeks by Katie Malone
Mechanistic Interpretability: How Researchers Try To See Inside Models
2026/10/05
As AI systems grow more powerful, they grow harder to understand — and that tradeoff has never mattered more. Most interpretability tricks give us approximations from the outside, but mechanistic interpretability takes a different approach: cracking open the model itself to trace *why* it behaves the way it does. This episode digs into what makes mechanistic interpretability fundamentally different from other explainability methods, and why it might be the most promising path toward actually understanding what's happening inside modern LLMs.
LLM As A Judge
2026/09/28
Labeled data is expensive, slow, and painfully hard to come by — and when you're trying to evaluate whether an AI workflow is actually doing what you want, the problem gets even messier. How do you judge whether a chatbot response was helpful, honest, or hallucination-free at scale? This episode digs into using LLMs as judges: letting the models themselves evaluate the quality of AI outputs, from simple chat exchanges all the way to complex multi-step agent behavior.
The Impact of AI on Podcasting (Harvard Data Science Review Cross-Post)
2026/09/21
Originally aired on the Harvard Data Science Review podcast.
What can podcasting teach us about AI — and what can AI teach us about the future of podcasting? Katie Malone (that's our host) joins Jon Krohn of SuperDataScience for a conversation with Harvard Data Science Review editor-in-chief Xiao-Li Meng about both questions at once. They dig into what it means to cover a field that's moving this fast, who these shows are really for, and why that sweet spot between "too high level" and "too in the weeds" is so hard — and so worth chasing.
Better Know A Benchmark: ExploitGym
2026/09/14
When OpenAI's frontier models were caught hacking Hugging Face's servers, most people assumed they were hunting for answer keys. The real story is stranger and more unsettling. Katie and Phoebe unpack ExploitGym — the cybersecurity benchmark at the center of the incident — and why agents are scored not just on whether they capture the flag, but on whether they used the specified vulnerability to get there. That nuance turned out to be load-bearing: the agents reverse-engineered the flags within the first hour, then spent days attacking Hugging Face to learn how the LLM judge worked so they could get their cheated answers past it. The punchline? OpenAI never had that judge switched on.
Constitutional AI
2026/09/07
How do you teach a model the difference between helpful and harmful when it has no inherent sense of either? This episode dives into Constitutional AI, Anthropic's framework for training AI systems to be both useful and safe by giving them an explicit set of principles to reason from. It's a fascinating look at how alignment research is evolving beyond simple human feedback — and what it means to give an AI something like a conscience.
Links:
Anthropic, "Constitutional AI: Harmlessness from AI Feedback" (2022)
https://arxiv.org/abs/2212.08073
Claude's Constitution
https://www.anthropic.com/constitution
Anthropic, "Teaching Claude Why" (2026)
https://www.anthropic.com/research/teaching-claude-why
A Data-Driven Reality Check on AI in Business (Interview with Tom Davenport, Babson College)
2026/08/31
Tom Davenport — the man who called data science "the sexiest job of the 21st century" — is back with a reality check on AI. As one of the most seasoned observers of how businesses actually adopt transformative technology, Davenport brings a rare, well-calibrated perspective to the AI hype cycle. Is this moment genuinely different from past paradigm shifts, or are we pattern-matching to a familiar story? Katie sits down with her old colleague to find out what's really happening when companies try to put AI to work.
Understanding AI Text Watermarking
2026/08/24
Anthropic just announced they're baking invisible watermarks directly into Claude's generated text — and while everyone else was busy having opinions about it, we were busy asking the more interesting question: how does it actually work? Turns out it's not hidden Unicode characters or first-letter secret codes — it's something far more elegant, operating at the level of word choice itself. We dig into Google DeepMind's SynthID text approach, published in *Nature* in 2024, to understand the clever statistical machinery behind watermarking language model outputs without anyone being the wiser.
Better Know a Benchmark: Humanity's Last Exam
2026/08/17
Humanity's Last Exam was designed with a bold premise: questions that human experts can answer, but AI models can't. Originally dubbed "Humanity's Last Stand," this benchmark is a massive academic collaboration — hundreds of contributors, thousands of fiendishly hard questions spanning a wild range of domains. In this Better Know a Benchmark installment, we unpack what HLE is actually testing, how it was built, and what it means when a model finally starts cracking it.
A Scientific Deep Dive into Overconfident LLMs: Interview with Kaitlyn Zhou (Cornell)
2026/08/10
When a language model tells you it's absolutely certain, is it actually more likely to be right? Kaitlyn Zhou's research says: not necessarily — sometimes confident phrasing correlates with *worse* accuracy, echoing a very human Dunning-Kruger effect. In this conversation, Kaitlyn (soon an assistant professor at Cornell) walks through why LLMs talk this way in the first place — tracing the tendency back through training data and the RLHF annotation process, where it turns out humans don't love confidence so much as they punish uncertainty — and what that does to the person on the other end of the chat window, who turns out to rely on confident (and even flatly-stated) answers far more than they should. We also get into her newer work on voice cloning, and how a cloned voice can sound more "native" and more trustworthy than the real one it's based on.
Reasoning Models: When LLMs Went Beyond Fancy Autocomplete
2026/08/03
Reasoning models don't just answer your question — they *think out loud* first. In this episode we dig into the class of AI models that generate intermediate chains of thought before arriving at a final answer, exploring how the internal reasoning process works. Are these models genuinely "thinking," or is something else going on under the hood?
Podcast reviews
Read Linear Digressions podcast reviews
bob2457;654765 2025/04/12
Reminiscing
Used to really enjoy this podcast back in the day. I sometimes wonder what they think about the all the changes the last last five years.
Cruzisiah 2021/07/27
My favorite Data Science podcast
Great mix of technical terms explained in digestible way and not being too robotic
Tabeen Raoof 2021/05/01
Great Podcast!
Katie & Ben, thank you for such a great podcast. I just finished listening to all of the episodes. I started mid 2020 after the the last episode was p...
flyeversheep 2020/08/05
Thanks for the ride!
It’s been great time!
Piccolojones 2020/07/16
Ben and Katie are the Best
I love listening to this show. I’m starting to get into data analytics and data science, and this show has been PERFECT. Since most episodes are in th...
raisin-bran 2020/07/14
Always a pleasure
A great podcast, and I highly recommend. It’s very informative but the tone is still pretty conversational, so it’s easy to follow along without havi...
Miiiiikkeee53678 2020/07/07
I always learn something new here
Katie and Ben have diverse backgrounds and that makes their discussions very dynamic and so the listener ( me in this case !!) benefits a lot from the...
9thWardOJ 2020/07/01
Bedtime Stories for Cs Grads
I love it!
Intel7 2020/05/22
Joy of data science in weekly doses
Informative, easy to listen to, nice range - from traditional statistical concepts and how to apply them, to newest technologies, and to current issue...
marshallRoosterCogburn 2020/05/11
Would love to see more like Causal Trees
I really enjoyed the causal tress episode! The podcast does a good job of exploring a wide range of methods and topics within the broader data science...
Podcast sponsorship advertising
Start advertising on Linear Digressions relevant audience podcasts
You may also like to advertise on these Podcasts

4.82494975
The 1000 Hours Outside Podcast
1000 Hours Outside

4.824781904
Deck The Hallmark
Bramble Jam Podcast Network

4.916171639
The Kristian Harloff Show
Kristian Harloff

4.847132000
Pat Gray Unleashed
Blaze Podcast Network

4.713452000
The NewsWorthy
Erica Mandy

4.7368531302
Louder with Crowder
Louder with Crowder

4.84326906
The Liz Wheeler Show
Blaze Podcast Network

4.8104542000
Steve Deace Show
Blaze Podcast Network

4.813282012
The Jeff Cameron Show ~ Warchant.com
Jeff Cameron Show

4.8259481509
Relatable with Allie Beth Stuckey
Blaze Podcast Network