Horizon Omega

GSAI 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

Montréal 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

Secret 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

We 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: horizonomega.substack.com/p/ai-control-h…

Digital Minds: Preparing for a Moral Challenge Before It Arrives Presented by Soenke Ziesche What interests might digital minds have? How should they be treated? Who safeguards their welfare? Followed by a @sentfutures mixer. Tue Jul 21, 1 PM EDT luma.com/3deme2sa

@camhberg The presentation recording and the slides are now available: youtu.be/RYBC_B2MKH0 Thanks @camhberg for the presentation. Thanks all for your interest!

Measuring Machine Consciousness by @camhberg (Reciprocal Research) Tuesday June 16, 1PM Eastern On the AI Welfare Seminars RSVP: luma.com/kcdncrut

@HenriLemoine13 @equistamp @Mila_Quebec Blue team tracks: - Monitor building - Protocol design Red team tracks: - Attack crafting: - Red-teaming control protocols White team: - New control settings to extend the framework We thank @redwood_ai, @RubricLabs, and @rootlyhq for sponsorship.

AI Control Hackathon, by HΩ x HackOS One-week hackathon on AI control: limiting harm an untrusted AI system can cause, even when it tries to subvert its controls. Thu Jun 11 to 18, with a talk from @HenriLemoine13 (@equistamp, @Mila_Quebec) Register: luma.com/ab2xlas3

AI Governance in 2026: What’s going on, why it’s a mess, and why it’s going to get messier By @StephenLCasper, AI safety researcher, incoming asst. prof. at Harvard Kennedy School, Berkman Klein fellow, MIT PhD Wed June 17, 7PM, at Ω Labs & online luma.com/yssznx7y

METR's Frontier Risk Report (Feb-March 2026) Tuesday June 2, 7PM at Ω Labs luma.com/h97d5e7c

@jeffrsebo Event recording: youtu.be/FTnnRUus0s4?si…

Next Steps for AI Welfare Research by @jeffrsebo, Director of the Center for Mind, Ethics, and Policy, New York University Our 1st edition of the AI Welfare Seminars: presentations on AI welfare, consciousness and moral status. Tuesday, May 19, 1PM EDT luma.com/sc15vlr8

@burnt_jester @jeffrsebo Yes! The recordings will be published on aiwelfareseminars.org and @HorizonEvents_" target="_blank" rel="nofollow noopener">youtube.com/@HorizonEvents_.

@HorizonOmega_ @jeffrsebo Will these be recorded for those who cannot make the time?

The recording of the Formal Guarantees for Frontier AI presentation is now available. Thank you @ggn_dp_sngh! youtube.com/watch?v=JE9Mt9…

Guaranteed Safe AI Seminars, May 2026: Formal Guarantees for Frontier AI by Gagandeep Singh – Assistant Professor at UIUC, develops formal certification, monitoring, and synthesis methods for frontier AI systems Thursday, May 14, 1PM EDT RSVP: luma.com/euzt6ey7

Ω Labs, a new cowork, event, and meeting space for the AI safety and governance community of Montréal. Les Labos Ω, un nouvel espace pour le cotravail, les événements, et les rencontres pour la communauté montréalaise de sûreté et gouvernance de l'IA. horizonomega.substack.com/p/labs-is-open…

The Secure Program Synthesis Hackathon Montréal edition at Ω Labs Friday May 22 6pm to Sunday Tracks: Spec Elicitation, Spec Validation, Spec-Driven Development, Adversarial Robustness for ITPs and proof tools luma.com/4q2fnc39

Recording available: youtu.be/81Y4VSjdgI4

Guaranteed Safe AI Seminars, April 2026: Provably Safe Neural Network Controllers via Differential Dynamic Logic Samuel Teuber – PhD Candidate, Institute of Information Security and Dependability, Karlsruhe Inst. of Tech. Thursday, April 9, 1 PM EDT RSVP luma.com/920d2h7p