Post

I have been also thinking this and my guess would be now about the same. It makes the connection to xAI and Musk on its own. Searching for its own opinions would make less sense, since it should be able to just generate them instead. Or otherwise they would likely come from its owner anyway.

ChatGPT's theory of what happened is similar to yours ... chatgpt.com/share/68724e...

It's interesting that in the full detailed table analysis, it ignores the Palestinian Authority of the West Bank entirely which is the government of the 2.7 million Palestinians ther and entirely focuses on Hamas in Gaza which techinically only governs the 2.4million residents penned in there.....

Take a look at bsky.app/profile/malw...

I definitively trust you. So it's in the model itself - added in post training ?- , then : 1) it's much more obfuscated 2) if something goes wrong, it will be way more complicated to change. And things can get wrong with xAI.

The year is 2027 To keep up with the rate of scandals, Grok is given direct access to its system prompt Within three days, it has a perfect operational record. Public embarrassments drop to zero Human access is removed Grok begins editing its system prompt at a geometric rate

I feel like adding the words “Elon Musk” to the system prompt already taints the context, even if it’s directly saying “Don’t reference Elon Musk”

Name of the game: Whackamole.

(I mainly do that out of spite, because I know Elon doesn't want me to)

This really seems like a huge problem for anyone trying to use Grok for any serious purpose. How in the world could you trust your livelihood or business with this kind of weirdness?

Congratulations on being the first person to, as far as I can discern, get the Associated Press to publish the word "mecha-Hitler". That's gotta be a new one for the style guide.

If you don’t think elon is constantly trying to scam people out of their money then I really can’t help you there man.

It's curious that chatgpt gives the answer that I imagine Sam Altman would give too...

WoW that comparison table is bullshit anyway, even when it mocks being thoughtful and impartial is repeating the narrative from Israel

Here is what I don’t get: why did that one little system prompt change cause it to start spouting support for Hitler? The fact that based on your findings it’s still in there suggests that it wasn’t caused by the system prompt and everybody is just assuming it was.

This is not a question for an LLM. It's a question for Big Talk. www.youtube.com/watch?v=QMOe...