Sentient Futures

Multi-agent AI alignment for pro-animal values

commitment
10 hrs/week
format
Research and writing · Creative project, product design, and entrepreneurship · Field-building, outreach, and coordination · Project scoping and preparing grant applications
topic
Post-AGI transition/Transformative AI · AI’s nearterm impact on animals · AI tools to empower advocates · Artificial sentience · Longtermism and future suffering · Macrostrategy, philosophy, and cause prioritisation
open to mentee proposals
Yes, with the right mentee
mentored by
Zoe Lu
Zoe LuSentient Futures
Apply by August 9 →

The project

This project has two parts:

  1. Part one is a continuation from the proof-of-concept built in the first cohort
  2. Part two applies the proof-of-concept specifically to pro-animal values. The proof-of-concept has demonstrated the complex social dynamics of AI alignment, both in terms of competition and cooperation among different AI agents and in terms of the bi-directional value feedback loop between parent countries and AI labs. During this incubator, the aims are both to polish the general framework and to deep dive into how this framework impact pro-animal values. The tentative plan is to have separate mentees working on part one and part two, with part two being more flexible in scope and design. Depending on the mentees' skills and interests, part two can be more or less technical. The deliverable for part one is a paper and the deliverable for part two can be a report, a paper, and/or an interactive tool.

The mentee's role

  • For part one: prioritize and execute on the next steps from the proof-of-concept, draft and polish a paper for publication
  • For part two: shape the emphasis of the project, research on the topics, and draft the output

Who I'm looking for

  • Must-have: proactive/agentic
  • Nice-to-have: good project management and communication skills

Questions for applicants

If you're interested in part two, please answer the following questions in a few bullets/sentences:

  1. How do you plan to adapt or evolve the proof-of-concept for pro-animal value alignment?
  2. What skills and experiences would you like to build during this project?

Support offered

  • Scoping/shaping direction
  • Project planning
  • Giving advice and feedback (on the specific project or more generally on career development)
  • Facilitating connections
  • Encouragement and accountability
  • Helping to prepare/rehearse presentations
Zoe Lu

Zoe Lu

Sentient Futures

Hello! I'm an AI×Animals field-builder, researcher, and policy advocate, with experience spanning animal advocacy, the AI ecosystem (including infrastructure, training, tools, governance), and the unique opportunities and challenges for animal welfare in the age of transformative AI.

I'm currently Community Lead at Sentient Futures. Besides community building, I contribute to technical projects as opportunities arise, having mentored a multi-agent AI alignment simulation during the last incubator. I also lead Faunalytics' AI strategy as a board member and provide freelance career advising for people interested in AI×Animals through the specialist networks at 80,000 Hours and Probably Good.

Previously, I worked as a R&D Technical Product Manager at Hudson River Trading and Two Sigma, where I scaled high-performance computing infrastructure and built best-in-class internal tools. I double majored in Computer Science and Mechanical Engineering, with a minor in Philosophy, from MIT, where I have conducted AI interpretability research in the context of self-driving cars.