Come on out to the next ACX (Astral Codex Ten) Montreal Meetup! This week, we're discussing To be legible, evidence of misalignment probably has to be behavioral, by Ryan Greenblatt. He argues that for evidence of misalignment to convince people to take strong action, it probably needs to be behavioral, and that internals-based methods (interpretability, ELK) alone are unlikely to be sufficiently persuasive.
Please also join the mailing list and our Discord server if you haven't already. We host biweekly ACX Montreal meetups, so join us if you don't want to miss any of them!
Come on out to the next ACX (Astral Codex Ten) Montreal Meetup! This week, we're discussing To be legible, evidence of misalignment probably has to be behavioral, by Ryan Greenblatt. He argues that for evidence of misalignment to convince people to take strong action, it probably needs to be behavioral, and that internals-based methods (interpretability, ELK) alone are unlikely to be sufficiently persuasive.
Optional readings:
- Safety isn't safety without a social model, by Andrew Critch
- The inaugural Redwood Research podcast, by Ryan Greenblatt and Buck Shlegeris
The podcast is great.
Please suggest topics or readings for future meetups on this form.
Venue: Ye Olde Orchard Pub & Grill, 20 Prince Arthur St W.
Date & Time: Saturday, January 17th, 2026, 2PM.
RSVP by clicking "Going" at the top of this post.
Send a message on our Montreal Rationalists Discord on channel #meetup-general if you have trouble finding us or any other issues.
Please also join the mailing list and our Discord server if you haven't already. We host biweekly ACX Montreal meetups, so join us if you don't want to miss any of them!
Posted on: