Episode

"Sequent: scale and automation for higher confidence in alignment" by Geoffrey Irving, Alex HT, Jesse Hoogland, Daniel Murfet, Jacob Pfau, Marco Cozzi, Stan van Wingerden

Podcast
LessWrong (Curated & Popular)
Published
Jun 10, 2026
Duration seconds
1389
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2037297/episodes/19328066-sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden.mp3
Audio
https://www.buzzsprout.com/2037297/episodes/19328066-sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden.mp3
JSON
/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden
Markdown
/podcast/lesswrong-curated-popular-5643401/sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/sequent-scale-and-automation-for-higher-confidence-in-alignment-by-geoffrey-irving-alex-ht-jesse-hoogland-daniel-murfet-jacob-pfau-marco-cozzi-stan-van-wingerden.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Alignment is not on track Artificial superintelligence (ASI) may be developed in the next few years. It is unclear whether alignment is on track to be ready on the same timeframe. At a minimum, the empirical programs at AI labs are unlikely to deliver a priori confidence, before training ASI, that things will go well. We are starting a large nonprofit research organization, Sequent, that aims to clear a higher bar: We are aiming at higher confidence via a portfolio of theory and empirics...