Horizon Omega

Advancing AI safety through collaboration, research, and education.
🦋

[Horizon Omega @HorizonOmega_]

Guaranteed Safe AI Seminars, August 2026:

Verifiable AI-Enabled Autonomous Systems with Conformal Prediction – @LarsLindemann2 (ETH Zurich)

Thursday, August 13, 1 PM EDT
https://t.co/FEFbsOEbuk

[Horizon Omega @HorizonOmega_]

Introducing ControlAI Canada

A presentation on the work @ControlAI 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 & on Zoom.
https://t.co/huC3wDCqqe

[Horizon Omega @HorizonOmega_]

AI Safety Papers We Love #4 - Law-Following AI: Designing AI Agents to Obey Human Laws

Talita Dias (intl lawyer) presents the case for AI agents that stay loyal to their principals only within legal bounds.

Tue Aug 11th 6-8 PM, at Ω Labs & on Zoom.
https://t.co/IOi6jsK2xY

[Horizon Omega @HorizonOmega_]

Community 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.

https://t.co/62i9zKTaOA

[Horizon Omega @HorizonOmega_]

Community 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.

https://t.co/CDDa2MATME

[Horizon Omega @HorizonOmega_]

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.
https://t.co/IRaDsUjM4B

[Horizon Omega @HorizonOmega_]

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. https://t.co/VGbNobrkiY

[Horizon Omega @HorizonOmega_]

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: https://t.co/fol5khdZNI

[Horizon Omega @HorizonOmega_]

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: https://t.co/fWaTNsadz3

[Horizon Omega @HorizonOmega_]

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
https://t.co/TxgTCUUx52

[Horizon Omega @HorizonOmega_]

@camhberg The presentation recording and the slides are now available: https://t.co/r5TWAlr7o5

Thanks @camhberg for the presentation. Thanks all for your interest!

[Horizon Omega @HorizonOmega_]

Measuring Machine Consciousness
by @camhberg (Reciprocal Research)

Tuesday June 16, 1PM Eastern
On the AI Welfare Seminars
RSVP: https://t.co/WiwJRp3mKl

[Horizon Omega @HorizonOmega_]

@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.

[Horizon Omega @HorizonOmega_]

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: https://t.co/I9PiKYQp4S

[Horizon Omega @HorizonOmega_]

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
https://t.co/4C5urRsFid

[Horizon Omega @HorizonOmega_]

METR's Frontier Risk Report (Feb-March 2026)

Tuesday June 2, 7PM at Ω Labs

https://t.co/iYKTFStwoD

[Horizon Omega @HorizonOmega_]

@jeffrsebo Event recording: https://t.co/jmnBl08AE0

[Horizon Omega @HorizonOmega_]

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
https://t.co/zAvIq4MHSb

[Horizon Omega @HorizonOmega_]

@burnt_jester @jeffrsebo Yes! The recordings will be published on https://t.co/PE3VF9nOih and https://t.co/StGaeagwrx.

[Horizon Omega @HorizonOmega_]

The recording of the Formal Guarantees for Frontier AI presentation is now available.

Thank you @ggn_dp_sngh!

https://t.co/n3cpo7MlF5

[Horizon Omega @HorizonOmega_]

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: https://t.co/9ttJmitbO5