Researcher at Unknown
Co-author of the stress-testing study on language model specifications
How media typically covers Andi Peng
Andi Peng as author
Over 300,000 stress-test scenarios reveal that frontier language models from Anthropic, OpenAI, Google DeepMind, and xAI prioritize values differently and expose thousands of hidden contradictions and ambiguities in model specifications.
“Author of "Stress-Testing Model Specs Reveals Character Differences Among Language Models" in Anthropic”