← Back to People
Founder of Humans& who previously worked on reinforcement learning and post-training of Claude 3.5-4.5 at Anthropic.
4
Mentions
3
Articles
2
Outlets
Oct 2025 — Oct 2026
Coverage
Positive
Sentiment
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Andi Peng
Article Types
- research1
Media Angles
- technical1
Appears In
Sentiment Distribution
Based on 3 scored articles
Positive 67%Neutral 33%
Associated AI Models
Claude1
Writes About
Appears Alongside
Articles
Most recent firstArticles Written
Andi Peng as author
Stress-Testing Model Specs Reveals Character Differences Among Language Models
AnthropicresearchneutralOct 27, 2025
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”
AI AlignmentFoundation ModelsAI SafetyLLMs
Also Mentioned In
Referenced in coverage
Anthropic opened applications for four-month research fellowships starting January 2027
AnthropicpositiveOct 16, 2026
“Conducted research stress-testing model specifications as part of Anthropic Fellows Program.”
A Three-Month-Old Startup Just Raised $480M at a $4.5B Valuation
TechCrunchcautiousJan 21, 2026
“Founder of Humans& who previously worked on reinforcement learning and post-training of Claude 3.5-4.5 at Anthropic.”