​​Tutke, The Finnish Center for Safe AI welcomes Katarina Slama and Olli Järviniemi from UK AI Security Institute to share about their journey and experience with UK AISI. There will be limited slots available. Presentations will be in English.

​Programme

• ​17:30-17:40: Opening remarks and introducing speakers

• ​17:40-18:10: Katarima Slama and Olli Järviniemi (UK AI Security Institute)

• ​18:10-18:30: Q&A

• ​18:30-20:00: Snacks, refreshments, open discussion and networking

​About Tutke

​​Tutke is an interdisciplinary non-profit organisation. We promote scientific understanding of secure development of artificial intelligence and support research and regulation leading to it.

​About UK AISI

​The AI Security Institute (AISI) is a research organisation within the UK government's Department for Science, Innovation and Technology working towards this goal: building the world's leading understanding of advanced AI risks and solutions, to inform governments so they can keep the public safe.

​About Katarina Slama

​Katarina Slama researches societal impacts of Transformative AI with UK AI Security Institute. Katarina has a PhD in Neuroscience from UC Berkeley, focusing on mechanisms of human attention allocation. Previously, Katarina worked as a Member of Technical Staff at OpenAI, where she contributed to the development of InstructGPT in the pre-ChatGPT era, and later worked on evaluations of societally relevant model behaviors.

​About Olli Järviniemi

​Olli Järviniemi is a project lead researching propensities and alignment of language models with UK AI Security Institute, and has previously completed a PhD in Mathematics at University of Turku. He specializes in AI control and deceptive alignment.