Designing systems to operate safely in real-world settings is a topic of growing interest in Machine Learning. As AI systems become more capable and widely deployed, it will become increasingly important that they are safe and beneficial. There is a large community of researchers focused on making current and future systems reliable and aligned with our objectives. For example, OpenAI, Anthropic, Inflection, and DeepMind all have safety teams.
Date and location
Tuesday November 29, 18:00 to 20:00 (CST).
Room 394 of the New Orleans Convention Center.
The event is published on the NeurIPS’s website.
Participating
To engage with the event meaningfully, we recommend to register and use Swapcard to request and schedule one-on-one meetings with other participants.
Related event
You are also invited to the AI Safety Unconference at NeurIPS 2022. It is happening on Monday November 28 near the Convention Center.
Visit the event website’s to apply.
The AI Safety Unconference brings together persons interested in aspects of AI safety, from technical AI safety problems to issues of governance of AI. As an unconference, it aims to foster valuable social interactions between participants, through moderated discussion groups, one-on-ones, lightning talks, free-form interactions.
Further information
Please read and respect AISE’s code of conduct.
The event is organized in partnership with the Center for AI Safety.
For any questions or feedback, reach out to info@aisafetyevents.org.
