Research | AI Alignment Foundation

What we're funding and accelerating to solve alignment.

What we're funding and accelerating to solve alignment. Read more about Modular Pretraining Enables Access Control Modular Pretraining Enables Access Control Dual-use knowledge enables models to assist us with the most difficult and demanding tasks in science, but it also empowers people who would use that knowledge to cause harm. Pre-training with GRAM enables knowledge to be siloed and turned on or off when deployed, so that a single model can be both safe and powerful. Read more about Self-Interpretation in Language Models via Adapter Probes Self-Interpretation in Language Models via…

saved by

• Senthilnathan Thirumurugan

related reading

• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
• Grant Application | AI Alignment Foundationaialignmentfoundation.org
• Modular Pretraining Enables Access Controlalignment.anthropic.com
• Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
• Research Areas in Methods for Post-training and Elicitation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignmentalignmentpretraining.ai
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
• Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment — LessWronglesswrong.com
• Research Areas in Interpretability (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org