The Alignment Mapping Program (AMP) launched in 2023 to develop independent thinking skills among AI safety researchers through an intensive 8-week curriculum.
Program overview and mission: AMP bridges the gap between foundational AI safety courses and advanced research programs by emphasizing active construction of mental models rather than passive learning.
- The program targets a critical need in AI safety education: developing researchers who can critically evaluate existing frameworks and generate novel approaches
- AMP’s curriculum focuses on having participants build their own comprehensive maps of the AI alignment problem space
- The program ran five cohorts in 2024 with approximately 25 total participants
Core curriculum structure: The program follows a three-phase approach designed to build independent thinking skills.
- Phase 1 (Weeks 1-3): Participants create visual maps of AI alignment problems, potential solutions, and personal contribution paths
- Phase 2 (Weeks 4-7): Students analyze established researchers’ work by comparing it to their own models through “shoulder mentors” – simplified frameworks of researcher approaches
- Phase 3 (Week 8): Participants develop concrete research plans and goals based on their mapped insights
Key program outcomes: Initial data from the pilot program revealed both successes and areas needing improvement.
- High engagement and positive feedback characterized the first three weeks of the program
- 60% of survey respondents recommended making AMP a core component of AI safety researcher education
- The program experienced significant participant drop-off (-30%) after week three
- Participants found initial reading requirements excessive and some exercises lacking clarity
Implementation improvements: Program administrators are making data-driven adjustments based on participant feedback.
- Restructuring weeks 4-7 to focus on fewer researchers or shift to a project-based approach
- Reducing reading requirements to 2-3 hours per week with tighter integration into mapping exercises
- Developing clearer exercise instructions and detailed examples of problem maps
- Exploring both in-person workshop formats and condensed 5-week versions
Future development plans: The program seeks to expand its impact through strategic partnerships and format innovations.
- Program leaders are seeking partnerships with other AI safety initiatives to incorporate AMP into existing curricula
- New program variations are being developed to address retention challenges while maintaining educational impact
- The team is actively soliciting community feedback on concepts like “shoulder mentors” and independent thinking development
Critical considerations: While AMP shows promise in developing independent thinking skills for AI safety researchers, its effectiveness will likely depend on successful implementation of feedback-driven improvements and careful attention to participant engagement patterns.
Recent Stories
DOE fusion roadmap targets 2030s commercial deployment as AI drives $9B investment
The Department of Energy has released a new roadmap targeting commercial-scale fusion power deployment by the mid-2030s, though the plan lacks specific funding commitments and relies on scientific breakthroughs that have eluded researchers for decades. The strategy emphasizes public-private partnerships and positions AI as both a research tool and motivation for developing fusion energy to meet data centers' growing electricity demands. The big picture: The DOE's roadmap aims to "deliver the public infrastructure that supports the fusion private sector scale up in the 2030s," but acknowledges it cannot commit to specific funding levels and remains subject to Congressional appropriations. Why...
Oct 17, 2025Tying it all together: Credo’s purple cables power the $4B AI data center boom
Credo, a Silicon Valley semiconductor company specializing in data center cables and chips, has seen its stock price more than double this year to $143.61, following a 245% surge in 2024. The company's signature purple cables, which cost between $300-$500 each, have become essential infrastructure for AI data centers, positioning Credo to capitalize on the trillion-dollar AI infrastructure expansion as hyperscalers like Amazon, Microsoft, and Elon Musk's xAI rapidly build out massive computing facilities. What you should know: Credo's active electrical cables (AECs) are becoming indispensable for connecting the massive GPU clusters required for AI training and inference. The company...
Oct 17, 2025Vatican launches Latin American AI network for human development
The Vatican hosted a two-day conference bringing together 50 global experts to explore how artificial intelligence can advance peace, social justice, and human development. The event launched the Latin American AI Network for Integral Human Development and established principles for ethical AI governance that prioritize human dignity over technological advancement. What you should know: The Pontifical Academy of Social Sciences, the Vatican's research body for social issues, organized the "Digital Rerum Novarum" conference on October 16-17, combining academic research with practical AI applications. Participants included leading experts from MIT, Microsoft, Columbia University, the UN, and major European institutions. The conference...