We conduct research on aligning Artificial Intelligence with the well-being of all sentient beings — work that is urgently needed before the technology outpaces our ability to guide it.
Learn More About Us →
New · Agentic Benchmark
In TAC (Travel Agent Compassion) the model acts as a tool-using booking agent, and nobody mentions animal welfare. All ten leaderboard models avoid the exploitation option less often than random chance; one welfare sentence in the system prompt lifts scores by 17 to 77 points.
Read the Blog Post →
Benchmark · with Mycelium
1,088 five-turn conversations that put animal-welfare values under sustained social, economic, and epistemic pressure. Four of seven frontier models shifted ranking once pushed.
Led by our partners at Mycelium, in collaboration with CaML.
Read the Blog Post →
Paper · Midtraining
Animal-welfare midtraining beat a matched urban-density control by 11 percentage points on ANIMA, and the same training also lifted compassion toward humans, an effect that survived subsequent instruction-tuning.
Read the Blog Post →
Community Initiative
An effort to build the world’s first and only mid-training corpus for animals and digital minds, seeding the training data of tomorrow’s AI with care for all sentient beings.
Visit the Site →
Live Leaderboard
Our public leaderboard tracking how frontier models treat sentient beings across ANIMA, MORU, and TAC, with per-question explorers. New models are added as they ship.
Visit CompassionBench →
Field Map
An interactive map of the organisations working on the risks advanced AI poses to sentient beings: who does research, who funds it, and how they connect.
Explore the Map →
Community Polls
Recurring polls asking the AI-safety community where it actually stands on seven contested questions spanning animal welfare, digital minds, partial-alignment stability, and multipolar competition. The results help steer CaML’s research agenda.
Vote on the EA Forum →Shaping AI values at the pretraining stage using synthetic documents, so positive behaviors persist through fine-tuning.
Measuring model compassion through custom benchmarks including the agentic TAC, plus older benchmarks ANIMA and MORU, with CompassionBench tracking frontier models.
Encouraging models to embrace uncertainty while caring deeply about the welfare of all sentient beings, reducing the chance of value lock-in.
Community Consensus
We polled the AI safety community on seven contested questions that shape our research agenda, spanning animal welfare, digital minds, partial-alignment stability, and multipolar competition.
Funded by:
CaMLCompassion Aligned Machine Learning.
Robustly improving the values of future AIs.
