Langsung ke konten
Global sound
Into AI Safety

Into AI Safety

Pretraining Safety w/ Ethan Roland

· 1 jam 28 mnt · Episode 32

Catatan episode

What if the safest AI models weren't built by adding guardrails after training, but by shaping what gets learned in the first place? Ethan Roland, senior alignment researcher at AE Studio and first author on an ICML 2026 spotlight paper, joins Jacob to talk about gradient routing, a technique that routes dangerous capabilities into isolated parts of a model's architecture where they can be locked or removed entirely. They get into the absorption effect, KYC-style access control frameworks, and what it would actually take for frontier labs to adopt this kind of work before it's needed rather…

Situs: kairos.fm

Live, satu jam terakhir: 9.254 lagu di 3.975 stasiun di 119 negara

Jelajahi dunia lewat radio

Cara lain untuk menjelajah (7)

Dengar sesuatu yang bagus? Simpan, atau langsung buka di Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
SFM RadioLanjut mendengarkan