We have 6 of 65 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Synthetic Hospital is an open, fully synthetic, fact-grounded longitudinal EHR benchmark that resolves the open sharing and verifiable ground truth barriers and is a difficult and realistic test of clinical AI performance.
This paper draws on lessons from social-science accounts of human-human collaboration and argues that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder and introduce new coordination challenges.
DECODE (Developer Edits of Code Dataset), a dataset of 53.6K real-world in-IDE code edits of AI-generated code in Python, TypeScript, and JavaScript, is introduced, and finetuning on DECODE enables open-source 3B models to perform code edit prediction tasks significantly better than frontier LLMs.
The results show that LLM agents, even without executing code, can identify many real-world reproducibility problems from paper-repository pairs, and ReproRepo can serve as a reusable, scalable framework for future evaluations of LLM agents on real-world reproducibility auditing.
While agents aid initial task completion, they harm users' code comprehension and thus do not prepare users to extend their code, and low-effort agent interaction types, like copy+paste prompts and auto-accepted edits, are linked with lower comprehension.
VibeJam, a browser-based user study platform for users to collaborate with AI agents to develop websites, and open-source VibeJam to spur extensions and support studies on how coding agents can help users.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
