UK AI Security Institute ICLR Social

​Join us for the UK AI Security Institute's ICLR Social to chat about research, policy, and how to make advanced AI go well.

​We'll have food and drinks at the venue, which is less than a 5 minute walk from the Singapore Expo.

​About AISI:

​We're a fast-paced research organisation inside the UK government working to advance mitigations research and get government to deeply understand frontier AI risks. Our research team is made up of around 70 technical staff, many of whom have joined from from places like Google DeepMind, OpenAI, and Anthropic.

​Some of our work includes:

• ​Pre-deployment evaluations of models such as OpenAI's o1 and Anthropic's Claude 3.5 Sonnet (new)

• ​Inspect, our open-source evaluation framework

• ​Frontier research on technical solutions for safeguards, control, and alignment

​We're scaling fast and have lots to do (we're hiring for research scientist and research engineer roles!). Learn more at aisi.gov.uk.