Women in Frontier AI x Allies - AI Safety, Security & Alignment
Calling all women, non-binary people and allies working in AI Safety, Alignment & Evaluation for an evening of discussion on building safer, better-aligned AI, exploring impending threats and preparing for challenges ahead.
Calling researchers and practitioners from METR, Apollo, Redwood Research, MATS Fellows, ARC, Epoch AI, Anthropic, Deepmind, OpenAI, Arena.ai etc.
Some topics of discussion:
Huggingface - OpenAI cyber attack. https://x.com/ClementDelangue/status/2079913058554585089
Scalable monitoring research agenda by Apollo - Automated red-teaming, evaluation datasets for monitoring
https://www.apolloresearch.ai/monitoring/a-scalable-monitoring-research-agenda/Should we push for no-fault liability for actions taken by AI? https://www.lesswrong.com/posts/Kj3YpqzhFySCjYcWi/we-should-push-for-no-fault-liability-for-actions-taken-by