Christopher Summerfield

Research focus

Constitutional AI & AI Ethics (2)Eval Frameworks & Benchmarks (2)Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

V. Weilnhammer (1)Lennart Luettgau (1)V. Sounderajah (1)Elise Wilkinson (1)

Papers (2)

Apr 28, 2026

V. Weilnhammer +63w ago

One-shot emergency psychiatric triage across 15 frontier AI chatbots

AI chatbots ace emergency psychiatric triage, but their tendency to over-triage low-risk cases reveals a critical gap in nuanced mental health assessment.

V. Weilnhammer, Lennart Luettgau, Christopher Summerfield +4

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Natural Language Processing

Feb 25, 2026

A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios

LLMs are surprisingly bad at helping with fraud and cybercrime, but cleverly disguised prompts and the removal of safety guardrails can significantly boost their criminal utility.

Kimberly T. Mai, Kimberly T. Mai, Anna Gausen +12

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Search

Christopher Summerfield

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)