Alignment for Animals

·EA Forum··

Published on May 5, 2026 4:00 PM GMTJasmine Brazilek & Miles Tidmarsh: Compassion in Machine LearningPreprint, March 2026: Full paper | HuggingFace resources | Animal Harm Benchmark (AHB)TL;DRMaking future transformative AI care about animals as well as humans is likely to massively affect the value of the future. There are people in labs who care, but they need benchmarks and methods that will scale. We provide a benchmark measuring thoughtful and realistic reasoning about animal welfare and te...

Read full article →

Related Articles

MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 2mo ago
Harm Laundering in GPT Models: Gender Discrimination Transformed Rather Than
sbulaev · Hacker News · 14d ago
Continual learning might make your blocking monitors nearly useless
Alex Mallen · Alignment Forum · 8d ago
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
Lukas Finnveden · Redwood Research · 10d ago
Can parts of the HuggingFace incident be simulated?
Benedikt Droste · LessWrong · 16d ago