Selective modularity: a research agenda — LessWrong
lesswrong.com · 7,853 words · saved by 1 readers
By training neural networks with selective modularity, gradient routing enables new approaches to core problems in AI safety.
x Selective modularity: a research agenda — LessWrong AI Frontpage 72 Selective modularity: a research agenda by cloud , Jacob G-W 24th Mar 2025 AI Alignment Forum 29 min read 3 72 Ω 29 Overview: By training neural networks with selective modularity, gradient routing enables new approaches to core problems in AI safety. This agenda identifies related research directions that might enable safer development of transformative AI. Introduction Soon, the world may see rapid increases in AI capabilities resulting from AI research automation, and no one knows how to ensure this happens safely ( Soare
related reading
- Gradient Routing: Masking Gradients to Localize Computation in Neural Networks — AI Alignment Forumalignmentforum.org
- Gradient Routing: Masking Gradients to Localize Computation in Neural Networks — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Modular Pretraining Enables Access Controlalignment.anthropic.com
- 2410.04332arxiv.org
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Auditing language models for hidden objectives — LessWronglesswrong.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- Thousand-dimensional structure — Resolutionresolution.org
- [2512.05648] Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMsarxiv.org