Aligning AI with human values | MIT News
4 Mins read
Senior Audrey Lorvo is researching AI safety, which seeks to ensure increasingly intelligent AI models are reliable and can benefit humanity. The growing…
A Case Study with the StrongREJECT Benchmark – The Berkeley Artificial Intelligence Research Blog
11 Mins read
When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden…
What is AI? | MIT Technology Review
2 Mins read
ALCON ENTERTAINMENT VIA ALAMY Right around the same time, Tegmark founded the Future of Life Institute, with a remit to study and…