Peter Peneder & Jasper Götting
Projects
Research Direction: Building next-generation evals for AIxBio
Test AI model’s ability to generate novel scientific hypotheses
Test for potential performance improvements from combining outputs from multiple AI models on the same task
Adapting evaluations to existing third-party agent scaffolds (e.g. FutureHouse, Google Co-Scientist)
What I'm looking for in a Mentee
Basic understanding of the AI+Biosecurity intersection
Familiarity with Python, and working with LLMs (ideally via API)
Scientific mindset (Thinking about potential biases, alternative explanations, positive/negative controls, …)
Research independence (i.e., being able to come up with and independently run small experiments, proactively generating and testing hypotheses, etc.)
Bio
Peter is a Research Scientist on SecureBio’s AI & Biotechnology Risks team. His work is focussed on building evaluations for assessing the biorisk posed by frontier AI models. Previously, during his PhD in bioinformatics, he developed multimodal deep learning approaches for biomedical data.
Jasper is a Research Scientist on SecureBio’s AI & Biotechnology Risks team. His work is focussed on building evaluations for assessing the biorisk posed by frontier AI models. Previously, he worked on biohardening and far-UVC air disinfection at Convergent Research and completed his PhD in virology.
