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
I like to iterate fast on different ideas. I think it's great if we spend each of the first few weeks trying a different idea and then choose one to dive into in more depth.
I haven't mentored for Pivotal before but think that groups of 1-3 mentees are probably best.
I like to meet with my mentees once a week, and also try to be responsive on slack to research updates.
Prior interpretability research experience isn't required, but I do think a strong research (e.g. current pursuing or have completed a PhD) or engineering (software, quant finance) background will result in the highest probability of a successful project
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.
