Funding 60 projects to advance AI alignment research | AISI Work
aisi.gov.uk · 945 words · saved by 1 readers
The Alignment Project welcomes its first cohort of grantees, and new partners join the coalition, bringing total funding to £27m.
AI systems are advancing quickly, and their potential is vast. To realise the benefits of more capable AI, we need confidence that powerful systems will do what we intend, even in complex, high-stakes settings. AI alignment is a crucial subset of that challenge. Alignment research asks how to build and deploy AI that follows human intent, avoids harmful side effects, and remains under human oversight and control. As systems become more capable and autonomous, methods that work for today’s models may not hold up tomorrow. That’s why we set up the Alignment Project , a global funding programme t
saved by
related reading
- Grant Application | AI Alignment Foundationaialignmentfoundation.org
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- Sequent: scale and automation for higher confidence in alignment — AI Alignment Forumalignmentforum.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
- Spring 2026 Projects - SPARsparai.org
- A minimal viable product for alignment - by Jan Leikealigned.substack.com
- Center for the Alignment of AI Alignment Centersalignmentalignment.ai
- Defining alignment research — LessWronglesswrong.com