Neat, weird.
I get similar results when I ask “What are the best examples of reward hacking in LLMs?” (GPT-4o). When I then ask for synonyms of “Thumbs-up Exploitation” the model still does not mention sycophancy but then I push harder and it does.
Asking “what is it called when an LLM chat assistant is overly agreeable and tells the user what the user wants to hear?” on the first try the model says sycophancy, but much weirder answers in a couple other generations. Even got a “Sy*cophancy”.
Neat, weird.
I get similar results when I ask “What are the best examples of reward hacking in LLMs?” (GPT-4o). When I then ask for synonyms of “Thumbs-up Exploitation” the model still does not mention sycophancy but then I push harder and it does.
Asking “what is it called when an LLM chat assistant is overly agreeable and tells the user what the user wants to hear?” on the first try the model says sycophancy, but much weirder answers in a couple other generations. Even got a “Sy*cophancy”.