x

AI ALIGNMENT FORUM

AF

michaelzhang — AI Alignment Forum

michaelzhang

michaelzhang

Message

31

Ω

17

1

1

10y

michaelzhang

31

Ω

17

10y

How robust are natural language autoencoders to initialization?

Natural language autoencoders are meant to take in an LLM's activation vector and describe in plain text what the model is thinking. However, its training data collection involves asking Claude to guess what a model might be thinking. How robust are NLAs to these guesses? We change Claude's guesses in...