Bay Area AI Safety Meetup # 8 w Scale AI and Holistic AI (sponsored by Holistic AI)

​October edition of the monthly academic salon discussing all aspects under the critical topic of AI safety.

​TLDR: Bringing together scholastic exercises with enterprise work in AI, this is a forum to discuss and address the deepest technical and ethical questions around AI safety in use within society. Primarily a social event to discuss current issues, featuring lightning talks while leaving more time for Q&A that could instigate a larger scope for any solutions.

​Not AGI-focused - this meetup is around scientifically-grounded solutions for issues in AI from development pov.

​This month sponsored by HolisticAI

​Talks this month:

• ​Satish Ramakrishnan, CTO @ Holistic AI

• ​Zifan (Sail) Wang, Research Scientist @ Scale AI, author and presenting the paper "LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet"

​Schedule:

• ​5:30pm - Doors / pizza

• ​6:30pm - Lightning Talks w Q&A (5-10 min)

• ​7:00pm - Discussion

• ​8:00pm - Shutting it down