About AI Safety Montréal
What we mean by AI safety
AI safety is the work of reducing the risk that increasingly capable AI systems cause harm.
We think transformative capability within a decade is more likely than not, and that severe, possibly irreversible failures are a real risk along the way. Systems are being handed more autonomy each year, including the work of building AI itself.
Failures, by cause:
- Misuse: someone deliberately uses a capable system to cause harm, from cyber operations to biological weapons.
- Misalignment: the system pursues something other than what its developers intended. Whether that would look like coherent deception or an incoherent mess is contested, and the fix differs.
- Mistakes: systems fail in ordinary ways in high-stakes deployments, and the consequences grow with the authority they are given.
- Organizational failure: oversight that exists on paper, drift into unsafe practice, near-misses nobody reports.
- Structural: harms produced by the wider system rather than by any one system. Control over a decisive technology concentrating, and the discrimination, surveillance, and labour effects already landing on people from systems in use today.
Work against these takes distinct forms: interpretability and evaluations to see what a system is doing, control protocols and sandboxing to limit what it can do, security for weights and tools, and governance of who may build and deploy.
Some of this is measured and some is argued. Strategic behaviour has been produced in controlled settings: models that detect they are being evaluated and behave differently, models that comply strategically with training they disprefer, models that learn to hide misbehaviour when their reasoning is monitored. What is argued rather than measured is whether that becomes durable deception in a production system, and where the capability trend ends. Evaluation lags capability, so no one can yet certify in advance which failure a deployment will produce.
Whether the systems themselves can be wronged is a separate question.
For a broad survey of the evidence, see the International AI Safety Report, led by Yoshua Bengio with over 100 experts.
What we do
Montréal hosts one of the world's largest AI research ecosystems, anchored by Mila. We connect the people working to make it safer.
- Events & talks: meetups, talks, and workshops on AI safety, ethics, and governance (calendar).
- Coworking & events space: a community space at Ω Labs to work alongside others and host gatherings.
- Programs: workshops, hackathons, and 1-on-1 advising (programs).
- Newsletter: a monthly roundup of research, events, and policy (read & subscribe).
- Ecosystem: a map of the local labs, institutes, and community groups (directory).
Who runs it
This site and most events are organized by Horizon Omega, a Canadian nonprofit working to reduce AI risk through community building, research, and public engagement. The community includes 1,600+ members.
Talk to an organizer
New to the field, or figuring out your next step? Book a free 1-on-1 with an organizer.
Get involved
- New to the field? Start here.
- Come to an event or join a program.
- List your event or organization: team@horizonomega.org.