Linear Digressions

✓

Przejęto

Umieść ten pasek wyszukiwania w swojej witrynie

WYSZUKAJ MINIONE ODCINKI

Wyszukaj minione odcinki Linear Digressions.

POPRZEDNIE ODCINKI 🔗

KV Cache Fundamentals

2 listopada 2026

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 wha…

00:24:16

AI Inference 101

26 października 2026

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 spotli…

00:27:37

Back Next Week

19 października 2026

Back Next Week by Katie Malone

00:00:18

Back in Two Weeks

12 października 2026

Back in Two Weeks by Katie Malone

00:00:21

Mechanistic Interpretability: How Researchers Try To See Inside Models

5 października 2026

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 t…

00:29:21

LLM As A Judge

28 września 2026

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 di…

00:30:12

The Impact of AI on Podcasting (Harvard Data Science Review Cross-Post)

21 września 2026

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-…

00:29:38

Better Know A Benchmark: ExploitGym

14 września 2026

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…

00:32:34

Constitutional AI

7 września 2026

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 fascin…

00:31:57