Sample language model responses to different varieties of English and native speaker reactions.
ChatGPT does amazingly well at communicating with people in English. But whose English?
Only 15% of ChatGPT users are from…
Category: AI
-
Virtual Personas for Language Models via an Anthology of Backstories – The Berkeley Artificial Intelligence Research Blog
-
A Case Study with the StrongREJECT Benchmark – The Berkeley Artificial Intelligence Research Blog
When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure languages. Excited by this result, we attempted to…
Continue Reading
-
The Visual Haystacks Benchmark! – The Berkeley Artificial Intelligence Research Blog
Humans excel at processing vast arrays of visual information, a skill that is crucial for achieving artificial general intelligence (AGI). Over the decades, AI researchers have developed Visual Question Answering (VQA) systems…
Continue Reading