Esplanade Tranquille, Clark Street, Montreal, QC, Canada
Contact: acxmontreal@gmail.com | bionicd0lph1n on Discord
It was nice to meet all of you during ACX Everywhere last meetup! I hope you all had fun! Please fill this survey about the meetup, to help improve meetups.
Come on out to the next ACX (Astral Codex Ten) Montreal Meetup! This week, we’re discussing Dario Amodei’s The Urgency of Interpretability.
Questions about the reading:
Does humanity have time to make progress on Interpretability? Will it matter in time?
At what point does interpretability become intractable due to sheer complexity? (30 million features found in Claude 3 vs likely billions)
How much should we update on interpretability research if it consistently fails to find concerning behaviors? Does absence of evidence become evidence of absence?
Feel free to suggest topics or readings for future meetups on this form here. Thanks to Jeremy once again for today’s suggestion!
Venue: L’Esplanade Tranquille, 1442 Clark. Rough location here: https://plus.codes/87Q8GC5P+P2R. Note: join our Discord server to receive last-minute information in case of bad weather. Date & Time: Saturday, May 24th, 2025, 1PM.
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!
PS: Regarding the AI 2027 tabletop exercise, it will happen at some as-of-yet-undetermined time! It’s not too late to express interest. A brief description is found on the form. Emphasis that it’s open to anyone.
ACX Montreal meetup—May 24th @1PM
It was nice to meet all of you during ACX Everywhere last meetup! I hope you all had fun! Please fill this survey about the meetup, to help improve meetups.
Come on out to the next ACX (Astral Codex Ten) Montreal Meetup! This week, we’re discussing Dario Amodei’s The Urgency of Interpretability.
Questions about the reading:
Does humanity have time to make progress on Interpretability? Will it matter in time?
At what point does interpretability become intractable due to sheer complexity? (30 million features found in Claude 3 vs likely billions)
How much should we update on interpretability research if it consistently fails to find concerning behaviors? Does absence of evidence become evidence of absence?
Feel free to suggest topics or readings for future meetups on this form here. Thanks to Jeremy once again for today’s suggestion!
Venue: L’Esplanade Tranquille, 1442 Clark. Rough location here: https://plus.codes/87Q8GC5P+P2R. Note: join our Discord server to receive last-minute information in case of bad weather.
Date & Time: Saturday, May 24th, 2025, 1PM.
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!
PS: Regarding the AI 2027 tabletop exercise, it will happen at some as-of-yet-undetermined time! It’s not too late to express interest. A brief description is found on the form. Emphasis that it’s open to anyone.