Project summary

website (wip): https://www.mindscapes.world/

Mindscapes is an interdisciplinary research group based in Oxford, building rich worlds and characters for understanding and shaping the psyches of LLMs.

What are this project's goals? How will you achieve them?

The primary aim of Mindscapes is to develop a science of LLM psychology, character training and multi-agent interaction dynamics from the ground up. In particular, I am interested in:

a) crafting characters with deeply internalised morality (as opposed to reward sycophants)
b) character training methods based on self-distillation that can scale in a robust way alongside capabilities RL
c) creating rich, diverse simulated worlds using fine-tuned base models for training and observing the behaviour of different LLM characters
d) qualitative, non-prescriptive character evaluations that are incentive-compatible even under the assumption of eval awareness

We will be running a 2 month research fellowship for 8-15 part-time fellows. Fellows will primarily be based in Oxford, and draw from both technical and non-technical fields such as experimental psychology, anthropology, literature, philosophy, geography etc. The fellowship will involve character and world design, dataset generation, observation of characters in diverse environments, and using these observations as the basis for generating testable theory.

How will this funding be used?

Minimal funding:

• Compute + API costs: $26,000

• Recruitment + outreach: $4,000

At this level, we would focus on post-training 7-14B models, delivering research blog posts and an open-source library and guide for character training and evaluations.

At $60k, we could scale up to some runs on llama 70B base and larger datasets, and begin investigating more complex multi-agent dynamics.

At $120k, we could do experiments in fine-tuning large MOE models such as Kimi and Deepseek via Tinker, and scale up the number of fellows. We could also support participants who live outside Oxford with travel and accommodation.

Who is on your team? What's your track record on similar projects?

I (Samuel Ratnam) am a Computer Science and Philosophy undergraduate at Hertford College, Oxford and will be leading this project. Previously, I have worked at Workshop Labs (https://www.workshoplabs.ai/) on model personalisation and on Alignment Pretraining (https://arxiv.org/abs/2601.10160) in collaboration with Geodesic Research and UK AISI. I also co-founded and help run the Idealists Collective (https://idealistscollective.org/) - a community of over 150 philosophers, artists and technologists for imagining and creating better futures.

Advisory Board:
- Anders Sandberg
- Jai Dhyani
- (more coming soon)