Mindscapes: World Building for AI Safety

An interdisciplinary research group based in Oxford for character training, model pyschology and multi-agent interaction dynamics

Welfare Red Teaming Competition

Crowdsourcing examples of where models do poorly on animal welfare so labs know what to fix

Sentient Futures Residency

Animal Welfare Midtraining Data Creation

Mycelium: AI alignment for nonhuman welfare

Artificial Selves

Integrating Selves and Research on Selves in the AI Community

Sentient Futures Project Incubator

Funding compute/API costs for Incubator projects that build nonhuman welfare consideration into AI safety work

Simulating Non-Dual Experience in LLMs via Activation Steering

Testing a geometric model of consciousness through mechanistic interpretability

CaML - AGI alignment to nonhumans

Training AI to generalize compassion for all sentient beings using pretraining-style interventions as a more robust alternative to instruction tuning

Do Language-Model Process Reports Track Their Underlying Computation?

Testing an architectural explanation for tension–flow reports during recursive self-focus

Synthetic pretraining to make AIs more compassionate

Enabling Compassion in Machine Learning (CaML) to develop methods and data to shift future AI values