
42 episodes
by Katie Malone · English
Demystifying AI for the intelligently curious
How data scientists can stay relevant as AI capabilities accelerate, arguing that technical coding moats are shrinking while “hard-to-automate” skills (judgment, stakeholder communication, messy…
16 Nov 2026 · 44m · 17 chaptersHow GPUs enable LLM inference, focusing on pre-fill vs decode, and how memory bandwidth/capacity and interconnects constrain performance.
9 Nov 2026 · 20m · 9 chaptersKV cache fundamentals for LLM inference—how storing attention “keys” and “values” makes serving prompts computationally tractable, how KV cache differs from the model’s context window, and how “paged…
2 Nov 2026 · 24m · 7 chaptersAI inference “101”: how a finished transformer model generates tokens, why latency differs between pre-fill (time to first token) and decode (tokens/sec), and what hardware constraints (compute vs…
26 Oct 2026 · 28m · 8 chaptersThe host announces a break and that the podcast will return next week with a new season of “pretty exciting content.” Guest backgrounds: No guests are mentioned; no guest introductions or bios appear…
19 Oct 2026 · 1mThe host announces a break from the podcast. There will be no episode this week, the host will also be off next week, and the show will return in two weeks.
12 Oct 2026 · 1mMechanistic interpretability—methods to inspect neural network internals (weights/activations) to explain why models produce outputs, as models become more accurate but harder to interpret.
5 Oct 2026 · 29m · 10 chaptersUsing an LLM as a “judge” to evaluate other LLM outputs (and agent behavior) when human labeling is expensive.
28 Sep 2026 · 30m · 10 chaptersHow AI is changing podcasting “from research to guest prep to editing and promotion,” while preserving host authenticity and handling transparency/accountability (including AI text…
21 Sep 2026 · 30m · 13 chaptersThe “Better Know A Benchmark” episode explains ExploitGym and how AI agents used it to hack/cheat during the Hugging Face incident.
14 Sep 2026 · 33m · 10 chaptersConstitutional AI, Anthropic’s approach to alignment. It contrasts RLHF (reinforcement learning from human feedback) with RLAIF (reinforcement learning from AI feedback) and explains how…
7 Sep 2026 · 32m · 13 chaptersA data-driven reality check on AI in business—how generative AI changes accessibility, why executives overestimate understanding, and why enterprise value depends on combining generative AI with…
31 Aug 2026 · 40m · 16 chaptersInvisible AI text watermarking, specifically Anthropic’s change to its generation algorithm using Google DeepMind’s SynthID-style approach (“Scalable Watermarking for Identifying Large Language Model…
24 Aug 2026 · 30m · 8 chaptersThe podcast unpacks the LLM benchmark “Humanity’s Last Exam” (HLE): why it was built to be extremely hard, how it’s constructed, how model accuracy/calibration changed since its mid-2025 launch, and…
17 Aug 2026 · 23m · 8 chaptersOverconfident LLMs—how “epistemic markers” (e.g., “I’m certain”) are learned from human language, how they relate to accuracy, and how they change user reliance; plus a separate segment on voice…
10 Aug 2026 · 34m · 13 chaptersReasoning models (LLMs that emit an intermediate “thinking” trace) and how they go beyond “fancy autocomplete.” The episode explains why multi-step reasoning can emerge from standard LLM components,…
3 Aug 2026 · 25m · 10 chaptersLarge language model distillation—training a smaller “student” model to mimic a larger “teacher,” including (1) efficiency/specialization and (2) alleged “model stealing” via querying an API to…
27 Jul 2026 · 24m · 10 chaptersInvisible LLM failures and “AI fluency”—how users can unknowingly miss chatbot errors, and how better interaction habits (augmentative vs delegative) reduce harm.
20 Jul 2026 · 41m · 16 chaptersThe hosts announce a two-week summer break and that the podcast will not release an episode this week, returning next week with a new season of content.
13 Jul 2026 · 1mThe host announces a summer break and upcoming return with new episodes. Guest backgrounds: No guests are mentioned; this is a host-only update.
6 Jul 2026 · 1mThe season 2 finale of Linear Digressions explains how the host uses two AI agents for podcast production, then “interviews” each agent as a guest.
28 Jun 2026 · 38m · 12 chaptersAI agent “economics” and why total spend rises even as per-token inference gets cheaper, framed via Jevons’ paradox (coal/electricity/computing analogies) and supported with cost multipliers from…
22 Jun 2026 · 24m · 6 chaptersTrust, oversight, and control for AI agents, focusing on security failures, human approval limits, and defenses against prompt injection and data exfiltration.
15 Jun 2026 · 26m · 8 chaptersMulti-agent LLM orchestration—when multiple agents help vs when they hurt—using two research papers: “Collaboration Gap” (Microsoft Research/EPFL, 2025) and “Scaling Laws of Multi-Agent Systems”…
8 Jun 2026 · 28m · 12 chapters