CompassioninMachineLearning/fortyK_synth_animals_8k_digital_minds_r64_cosine_lr5e-6_plainprompt
Text Generation • 8B • Updated • 7
None defined yet.
HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation