AI Safety | Arkose

AI Safety Resources

AI Safety | Arkose Learn about large-scale risks from advanced AI Selected Papers --> --> --> Overviews What types of risks from advanced AI might we face? These papers provide an overview of anticipated problems and relevant technical research directions. (Ngo et al., 2022) The Alignment Problem from a Deep Learning Perspective (Hendrycks et al., 2023) An Overview of Catastrophic AI Risks (Chan et al., 2023) Harms from Increasingly Agentic Algorithmic Systems (Anwar et al., 2024) Foundational Challenges in Assuring Alignment and Safety of Large Language Models Dangerous Capability Evaluations

saved by

• Ayodeji Adesegun

related reading

• Want to upskill in technical AI safety? Here are 67 useful resources | 80,000 Hours80000hours.org
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• Reading Listblog.redwoodresearch.org
• AI safety - Wikipediaen.wikipedia.org
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• Using Dangerous AI, But Safely?youtube.com
• Is China Serious About AI Safety? | AI Frontiersai-frontiers.org