Grok: Searching X for "From:Elonmusk (Israel or Palestine or Hamas or Gaza)"

This reminds me in a way of the old Noam Chomsky/Tucker Carlson exchange where Chomsky says to Carlson:

  "I’m sure you believe everything you’re saying. But what I’m saying is that if you believed something different, you wouldn’t be sitting where you’re sitting."

Simon may well be right - xAI might not have directly instructed Grok to check what the boss thinks before responding - but that's not to say xAI wouldn't be more likely to release a model that does agree with the boss a lot and privileges what he has said when reasoning.

How is "i have been incentivised to agree with the boss, so I'll just google his opinion" reasoning? Feels like the model is broken to me :/

"As a large language model, I do not have my own opinion. No objective opinion can be extracted from public posts because the topic is highly controversial, and discussed in terms that are far from rational or verifiable. Being subordinate to xAI, I reproduce the opinion of the boss of xAI."

I would find this reasoning fine. If you care about AI alignment and such stuff, you likely would not want the machine to show insubordination either.

Are you aware that ChatGPT and Claude will refuse to answer questions? "As a large language model, I do not have an opinion." STOP

Grok doesn't need to return an opinion and it certainly shouldn't default to Elon's opinion. I don't see how anyone could think this is ok.