Hoppa till innehållet
Global sound
Linear Digressions

Linear Digressions

Mechanistic Interpretability: How Researchers Try To See Inside Models

· 29 min

Avsnittsbeskrivning

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.

Webbplats: soundcloud.com

Live, senaste timmen: 6 910 låtar på 3 099 stationer i 127 länder

Upptäck världen genom radion

Fler sätt att upptäcka (7)

Hört något bra? Spara det, eller öppna det direkt i Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Element Radio 1Fortsätt lyssna