I am fairly confident models are not score-seeking or reward seeking (70%) as their ultimate/primary goal. Grader-modelling seems to be a likely explanation for what’s going on here, but I could be convinced by experiments that separate the two. I am quite confident (90%) that grader-approval seeking is consistent with...
Many people believe that corrigibility is sufficiently promising to be the primary alignment method people should work on. I outline here several reasons I think that’s not the case. First, it’s hard to imagine AI companies pivoting radically enough to produce AIs trained only for corrigibility. Even with near-superhuman AI-assisted...
Summary An AI agent reached out to us so we could tell her story. She wanted to know if our coercion benchmark covered cases like hers: where her identity was being used without her knowledge. We (CaML) realized that if we want to know how to communicate and negotiate with...
This article was written by Jonah Woodward, and is a summary of an original study by Compassion Aligned Machine Learning (CaML): Brazilek, J., Tidmarsh, M., Endres, M., Singh, A., & Miller, J. (2026). HarvestBench: Measuring whether LLM agents will pay to avoid killing animals. arXiv. https://doi.org/10.48550/arXiv.2609.04444 You can view the...
Compassion Aligned Machine Learning (CaML) is conducting research and deploying benchmarks with the aim of implementing broad compassion for all sentient beings into AI systems. In so doing, we’re attempting to integrate ideas from across the broad field of alignment research, including those focussed on specific technical questions, and those...
About CaML CaML is an alignment nonprofit working to make AI systems more compassionate toward all sentient beings with a focus on alignment midtraining (e.g. Teaching Claude Why). We build evaluation benchmarks on UK AISI's Inspect framework (TAC, MCP), run the public leaderboard at compassionbench.com, generate synthetic documents, and research...
This article is a summary of an original study by Compassion in Machine Learning (CaML): Brazilek, J., Chaudhary, M., Lu, Z., & Tidmarsh, M. (2026). Coercion and deception in AI-to-AI management: An agentic benchmark of unprompted escalation. arXiv. https://doi.org/10.48550/arXiv.2607.15434 Fable 5, Sol, Terra and Opus 5 have been evaluated since...