Jasmine Brazilek

What is the Alignment Community Thinking?

by jonahmattwoodward, MilesTS, Jasmine Brazilek, and Maheep Chaudhary

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...

Sep 65

Research scientists for CaML: Investigating whether mid-training can survive RL

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...

Sep 116

Coercion and Deception in AI-to-AI Management

by jonahmattwoodward, Jasmine Brazilek, MilesTS, and Maheep Chaudhary

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...

Aug 1012

Community Polls on Alignment Controversies II

by jonahmattwoodward, MilesTS, and Jasmine Brazilek

Please spend <5 minutes filling in the below polls on AI alignment! Thank you to everyone who filled out last month's polls. It was great to see 60+ comments engaging with these issues. This month’s survey has already been taken by a panel of 15 alignment researchers, including Scott Alexander...

Jul 309

Would your AI travel agent book a bullfight? Testing whether agents consider animal welfare without being prompted

by jonahmattwoodward, Jasmine Brazilek, Maheep Chaudhary, Oliver Tullio, Joel Christoph, and MilesTS

This article reflects new updates to the accompanying paper: arxiv.org/abs/2606.18142. Benchmark: now included in the UK AI Security Institute's Inspect Evals. Leaderboard: compassionbench.com/tac. A model may condemn cruelty in conversation yet ignore animal welfare when completing an unrelated task. Stated concerns matter little if they do not affect decisions. We...

Jul 1713

Assert, don't describe: how writing style in training data shapes an AI's moral stance

tl;dr The way things are said ("linguistic features") in fine-tuning data affect AI alignment. Some features degrade alignment to the value targeted in the corpus, some have negligible impact, and others bolster it. We recommend you become familiar with these features if your writing may end up in LLM training...

Jun 172

[Linkpost] Community polls on alignment controversies

Planning where we focus at CaML requires forming views on many controversial questions. In many cases, people we've talked to have wildly different perceptions of the balance of opinions, so we thought this would be a great way for us and others to know where we're out of step on...

Jun 178

Jasmine Brazilek

Jasmine Brazilek

Research scientists for CaML: Investigating whether mid-training can survive RL

Would your AI travel agent book a bullfight? Testing whether agents consider animal welfare without being prompted

Coercion and Deception in AI-to-AI Management

Document-tuning instills durable animal compassion in LLMs (and generalizes to humans)

Jasmine Brazilek

Research scientists for CaML: Investigating whether mid-training can survive RL

Would your AI travel agent book a bullfight? Testing whether agents consider animal welfare without being prompted

Coercion and Deception in AI-to-AI Management

Document-tuning instills durable animal compassion in LLMs (and generalizes to humans)

What is the Alignment Community Thinking?

Research scientists for CaML: Investigating whether mid-training can survive RL

Coercion and Deception in AI-to-AI Management

Community Polls on Alignment Controversies II

Would your AI travel agent book a bullfight? Testing whether agents consider animal welfare without being prompted

Assert, don't describe: how writing style in training data shapes an AI's moral stance

[Linkpost] Community polls on alignment controversies