Clément Dumas

I'm a CS master's student at ENS Paris-Saclay. I want to pursue a career in AI safety research


Sorted by New

Wiki Contributions


Thanks for the great post, I really enjoyed reading it! I love this research direction combining unsupervised method with steering vector, looking forward to your next findings. Just a quick question : in the conversation you have in the red teaming section, is the learned vector applied to every token generated during the conversation ?

Let's assume the prompt template is  Q [true/false] [banana/shred]

If I understand correctly, they don't claim   learned has_banana but  learned has_banana. Moreover evaluating  for  gives:

Therefore, we can learn a  that is a banana classifier