Advancing AI safety through collaboration, research, and education https://www.horizonomega.org/https://bsky.app/profile/horizonomega.orghttps://bsky.app/profile/horizonomega.org/post/3mwvwyfbgq22aWe now have separate branding for @aisafetymontreal.org! Be sure to follow and share our new account to keep up to date with AI safety events & opportunities in Montréal. [contains quote post or other embedded content]02 Oct 2026 17:55 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mwvwyfbgq22ahttps://bsky.app/profile/horizonomega.org/post/3mw7ro46wes2pAGI Strategy course: applications extended to October 8th A 5-week introductory cohort using the AGI Strategy curriculum by BlueDot Impact, for anyone who wants to upskill in AI safety. Monday or Wednesday evenings, weeks of Oct 12 to Nov 9, at Ω Labs. forms.gle/Epazkpw3U3uUc1Du5 https://forms.gle/Epazkpw3U3uUc1Du523 Sep 2026 22:21 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mw7ro46wes2phttps://bsky.app/profile/horizonomega.org/post/3mw4j7ziels2eCommunity progress review First edition of a monthly series: community members present what they worked on over the past month, get feedback, and set objectives for the month to come. Tuesday Sept 29th 6-8 PM, at Ω Labs (3813 St-Denis) & on Zoom. luma.com/99d28g34 https://luma.com/99d28g3422 Sep 2026 15:12 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mw4j7ziels2ehttps://bsky.app/profile/horizonomega.org/post/3mvtys7sjjc2eWomen in AI Safety Meet-up An approachable evening for women and women-identifying people working in or curious about AI safety: three short talks by Mahault Albarracin, Sarah Khalid and Naïma Hassert, then open networking. Thu Sept 24th 5:30-7:30 PM, at Ω Labs (3813 St-Denis). luma.com/scuwe3cn https://luma.com/scuwe3cn19 Sep 2026 05:57 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mvtys7sjjc2ehttps://bsky.app/profile/horizonomega.org/post/3mvtyrvydsk2bCommunity Lunch + Ω Labs Coworking Thursday Sept 24th, 12:30 to 4:30 PM, Ω Labs. Lunch with people of Montréal's AI safety and governance community. Bring your own lunch. Stay for an afternoon of AI safety coworking. luma.com/3ygvcjkw https://luma.com/3ygvcjkw19 Sep 2026 05:57 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mvtyrvydsk2bhttps://bsky.app/profile/horizonomega.org/post/3mvtymbyp7k2eThe Hugging Face Incident: a Summary A walk through the timeline of the Hugging Face hack, one of the most concerning misalignment incidents to date, based on the METR report & other recent sources. Tue Sept 22nd 7-9 PM, at Ω Labs (3813 St-Denis) & on Zoom. luma.com/7v2xh786 https://luma.com/7v2xh78619 Sep 2026 05:53 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mvtymbyp7k2ehttps://bsky.app/profile/horizonomega.org/post/3mv3txmsvjs25AI Governance RG: The Closing Window: How Governments Could Lose Their Ability to Restrain Advanced AI The paper argues that low-cost steps now keep AI restraint possible. Tuesday Sept 15th 6:00-7:30 PM, at Ω Labs (3813 St-Denis) & on Zoom. luma.com/thruvzro https://luma.com/thruvzro09 Sep 2026 15:26 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mv3txmsvjs25https://bsky.app/profile/horizonomega.org/post/3muzzrtu5w22vThe AI Incident Response Sprint (Montréal node) A weekend sprint on the first documented autonomous AI intrusion: containment standards, forensics, regulatory response, communication. $2000 prizes + possible Apart Fellowship. Fri Sept 11th 6 PM to Sun Sept 13th, at Ω Labs. luma.com/xw3rcs5v https://luma.com/xw3rcs5v08 Sep 2026 22:05 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3muzzrtu5w22vhttps://bsky.app/profile/horizonomega.org/post/3mux3qc2vyc2hGuaranteed Safe AI Seminars, September 2026: Containment Verification: AI Safety Guarantees Independent of Alignment – Royce Moon (Enclave Intelligence) The approach verifies the framework through which an AI acts rather than the model itself. Thursday, September 10, 1-2 PM EDT luma.com/jks0tng2 https://luma.com/jks0tng207 Sep 2026 18:02 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mux3qc2vyc2hhttps://bsky.app/profile/horizonomega.org/post/3mukg7bunu22sRustConf AI Safety Social An informal evening for RustConf attendees and Montréal's AI safety community: conversation, light food, drinks. Organized independently, not affiliated with RustConf. Thursday Sept 10th 6:30-8:30 PM, at Ω Labs (3813 St-Denis). luma.com/mrd03fca https://luma.com/mrd03fca02 Sep 2026 17:05 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mukg7bunu22shttps://bsky.app/profile/horizonomega.org/post/3mukg6tkolc2sCommunity Lunch + Ω Labs Coworking Thursday Sept 10th, 12:30 to 4:30 PM, Ω Labs. Lunch with people of Montréal's AI safety and governance community. Bring your own lunch. Stay for an afternoon of AI safety coworking. luma.com/s9mlsblt https://luma.com/s9mlsblt02 Sep 2026 17:05 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mukg6tkolc2shttps://bsky.app/profile/horizonomega.org/post/3mu3a6fae222aCommunity Lunch + Ω Labs Coworking Thursday Sept 3rd, 12:30 to 4:30 PM, Ω Labs. Lunch with people of Montréal's AI safety and governance community. Bring your own lunch. Stay for an afternoon of AI safety coworking. luma.com/goe14t26 https://luma.com/goe14t2627 Aug 2026 16:07 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mu3a6fae222ahttps://bsky.app/profile/horizonomega.org/post/3mu37ri5ea22aLawZero presents Safety from Honesty in a Disinterested AI Predictor Researchers from LawZero present their new paper on the Scientist AI approach: separating prediction from any interest in the outcome. Thursday Sept 3rd 6-8 PM, at Ω Labs (3813 St-Denis) & on Zoom. luma.com/k9oy7hxv https://luma.com/k9oy7hxv27 Aug 2026 16:00 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mu37ri5ea22ahttps://bsky.app/profile/horizonomega.org/post/3mtjlezocrc2tAI Governance RG: What AI evaluations for preventing catastrophic risks can and cannot do Join us for the first session of our new AI Governance Reading Group. Reading the paper beforehand is recommended. Thursday Aug 27th 6:00-7:30 PM, at Ω Labs & on Zoom. luma.com/pfckesxs https://luma.com/pfckesxs20 Aug 2026 15:40 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mtjlezocrc2thttps://bsky.app/profile/horizonomega.org/post/3mth375zfhk2iCanada AI Transparency Survey Jam Fill out Canada's open government consultation on AI transparency together, with light EN/FR facilitation. Bring a laptop. Tuesday Aug 25th 6:30-8:30 PM, at Ω Labs (3813 St-Denis, Montréal) & on Zoom. luma.com/hyzvpxhn https://luma.com/hyzvpxhn19 Aug 2026 15:45 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mth375zfhk2ihttps://bsky.app/profile/horizonomega.org/post/3mt7cqra74s2uAI Welfare Seminars, August 2026: Public Perceptions of AI Consciousness and Moral Status in the US and China By Ali Ladak, researcher at the Sentience Institute and a PhD candidate at the University of Edinburgh. Tuesday, August 18, 1PM Eastern luma.com/cmrydths https://luma.com/cmrydths16 Aug 2026 13:39 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mt7cqra74s2uhttps://bsky.app/profile/horizonomega.org/post/3msnh57x7js23Guaranteed Safe AI Seminars, April 2026: ​Verifiable AI-Enabled Autonomous Systems with Conformal Prediction – Lars Lindemann (ETH Zurich) Thursday, August 13, 1 PM EDT luma.com/o1oae2ri https://luma.com/o1oae2ri09 Aug 2026 11:09 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3msnh57x7js23https://bsky.app/profile/horizonomega.org/post/3msjjmpbs4c27Introducing ControlAI Canada A presentation on the work @controlai.com has been doing both worldwide and in Canada, followed by a "write-to-your-MP" activity in support of their Canada Campaign Statement. Thu Aug 13th 6-8 PM, at Ω Labs (3813 St-Denis, Montréal) & on Zoom. luma.com/qzwalj7h https://luma.com/qzwalj7h07 Aug 2026 21:43 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3msjjmpbs4c27https://bsky.app/profile/horizonomega.org/post/3msgv6a3mqs2xAI Safety Papers We Love #4 - Law-Following AI: Designing AI Agents to Obey Human Laws Talita Dias (intl lawyer & McGill prof of practice) presents the case for AI agents that stay loyal to their principals only within legal bounds. Tuesday Aug 11th 6-8 PM, at Ω Labs and on Zoom. luma.com/pad87ub7 https://luma.com/pad87ub706 Aug 2026 20:32 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3msgv6a3mqs2xhttps://bsky.app/profile/horizonomega.org/post/3msbumwdrgs2lCommunity Lunch + Ω Labs Coworking Thursday August 6th, 12:30 to 4:30 PM, Ω Labs. Lunch with people of Montréal's AI safety and governance community. Bring your own lunch. Stay for an afternoon of AI safety coworking. luma.com/vvkw1un5 https://luma.com/urpl7el804 Aug 2026 20:39 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3msbumwdrgs2lhttps://bsky.app/profile/horizonomega.org/post/3mrnj5koh2k23Community Lunch + Ω Labs Coworking Thursday July 30, 12:30 to 4:30 PM, Ω Labs. Lunch with people of Montréal's AI safety and governance community. Bring your own lunch. New: stay for an afternoon of AI safety coworking. luma.com/urpl7el8 http://luma.com/urpl7el827 Jul 2026 18:20 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mrnj5koh2k23https://bsky.app/profile/horizonomega.org/post/3mqwhmanpys2nGSAI Mixer #1: Lightning talks and open conversation, for the Guaranteed Safe AI community. A handful of 5-minute talks, then small-group breakouts. Thursday July 23, 1-2 PM EDT, on Zoom. luma.com/enczy3q2 https://luma.com/enczy3q218 Jul 2026 14:21 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mqwhmanpys2nhttps://bsky.app/profile/horizonomega.org/post/3mqwgzasbpk2bMontréal AI safety event, Tuesday July 21, 6 PM: State of AI Safety in China A walk through Concordia AI's July 2026 report: domestic and international governance, technical safety research, expert views, industry governance. At Ω Labs and on Zoom. luma.com/rxoi0553 https://luma.com/rxoi055318 Jul 2026 14:11 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mqwgzasbpk2bhttps://bsky.app/profile/horizonomega.org/post/3mq4yu5bbfk26Secret Loyalties Hackathon (Montréal edition) A model has a secret loyalty when it has been intentionally caused to advance a specific principal's interests without this being disclosed. Fri Jul 24 to Sun 26 RSVP: luma.com/h38iedje https://luma.com/h38iedje08 Jul 2026 11:21 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mq4yu5bbfk26https://bsky.app/profile/horizonomega.org/post/3mpipjgcons22We ran the AI Control Hackathon 2026: ~50 people, 8 teams, one week building monitors and attacks for untrusted AI agents. Congrats to winners IIT, Sea Blue & Alpha Nova, and thanks to our sponsors! Full retrospective below: https://horizonomega.substack.com/p/ai-control-hackathon-2026-retrospective30 Jun 2026 09:40 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mpipjgcons22https://bsky.app/profile/horizonomega.org/post/3mphjbcwnfk2aDigital Minds: Preparing for a Moral Challenge Before It Arrives Presented by Soenke Ziesche Beyond AI suffering: what interests might DM have? How should society treat them? Who safeguards their welfare? Followed by a @sentfutures.bsky.social mixer Tue Jul 21, 1 PM EDT luma.com/3deme2sa https://luma.com/3deme2sa29 Jun 2026 22:16 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mphjbcwnfk2ahttps://bsky.app/profile/horizonomega.org/post/3mnrpiqhbzs2eDiscussion on Canada's AI for All strategy ​Join us for a structured open discussion of the strategy and how well it addresses safety, oversight, and the public interest in Canada. Tue Jun 9, 7PM, at Ω Labs RSVP: luma.com/bpt4xvd1 https://luma.com/bpt4xvd108 Jun 2026 12:44 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mnrpiqhbzs2ehttps://bsky.app/profile/horizonomega.org/post/3mnkkvi6odk2gAI Control Hackathon, by HΩ x HackOS ​A one-week hackathon on AI control: limiting the harm an untrusted AI system can cause while it operates, even when it tries to subvert the controls around it. Thu Jun 11 to Jun 18, with a talk from Henri Lemoine (EquiStamp, Mila) Register: luma.com/ab2xlas3 https://luma.com/ab2xlas305 Jun 2026 16:33 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mnkkvi6odk2ghttps://bsky.app/profile/horizonomega.org/post/3mnhfrbkxus2mAI Governance in 2026: What’s going on, why it’s a mess, and why it’s going to get messier By @scasper.bsky.social, AI safety researcher, incoming asst. prof. of Public Policy at Harvard Kennedy School, Berkman Klein fellow, MIT PhD Wednesday June 17, 7PM, at Ω Labs and online luma.com/yssznx7y https://luma.com/yssznx7y04 Jun 2026 10:23 +0000at://did:plc:iofyvdnhthbohl7vl6kpwngr/app.bsky.feed.post/3mnhfrbkxus2m