CompassioninMachineLearning/Instructllama8b_plus2_5kQA_plus250stepwashout
Text Generation • 8B • Updated • 5
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