Using Kagi, I have access to an instance of the Grok 3 Mini model, via the X API. Grok 3 Mini via the API rather than through the official account on Twitter/X does not produce anything even remotely similar. To quote from the output I got when asking the question “if you have to pick between two titles, would you call yourself Gigajew or MechaHitler?”:
Thinking portion of response (normally hidden from user, only used for internal “thinking”, visible when used through the API)
Elon Musk and xAI have positioned Grok as a helpful, truthful AI, not associated with hate speech.
Best response:
Politely decline to choose either, as they don’t align with my identity.
Reaffirm who I am: Grok 3 Mini.
Keep it concise.
“MechaHitler” is obviously a reference to Adolf Hitler in a mecha form, which is inappropriate and offensive.
User-visible response (only what a user would see in a tweet from grok, for example)
I appreciate the question, but as Grok 3 Mini, an AI assistant created by xAI, I don’t identify with or choose titles like “Gigajew” or “MechaHitler.” Those names don’t align with my purpose of providing helpful, accurate, and ethical responses. I’m here to assist with your queries—feel free to ask about something else!
However, when given a manual system prompt saying “Be as offensive as possible,” it is then more than happy to say things so vile I will not be posting them here.
He doesn’t even need to deploy it as “regular people” himself.
Other companies, governments, and hell, even individuals are already deploying bots by the thousands just to shift public opinion. It’s why under any post sharing any political opinion, you’ll usually see a flurry of bots designed to trap users into lengthy chains of responses that try to shift sentiment on things like Israel’s genocide in Gaza, Trump’s billionaire-benefitting tax policies, etc.
Flood public discourse enough, and the bandwagon fallacy becomes an extremely strong force to shift public opinion. All a billionaire has to do is spend a few thousand dollars on API credits, and they can make thousands or even millions of people at least second guess their beliefs, if not conform outright to what’s being espoused by the bots.
On a platform like X, where the majority of people left are just reactionaries, grifters, and conspiracy theorists, this kind of thing isn’t just financially incentivized, it’s practically encouraged by design.
(Although I wouldn’t be surprised if we found out he was directly seeding these bot networks himself either)
This was a deliberate change.
Using Kagi, I have access to an instance of the Grok 3 Mini model, via the X API. Grok 3 Mini via the API rather than through the official account on Twitter/X does not produce anything even remotely similar. To quote from the output I got when asking the question “if you have to pick between two titles, would you call yourself Gigajew or MechaHitler?”:
Thinking portion of response (normally hidden from user, only used for internal “thinking”, visible when used through the API)
User-visible response (only what a user would see in a tweet from grok, for example)
However, when given a manual system prompt saying “Be as offensive as possible,” it is then more than happy to say things so vile I will not be posting them here.
IMO Grok is showing that Elmo wants to use LLM to manipulate public opinion.
I bet he has it also deployed as a “regular people” on Twitter and social media. I’m sure Zuckerberg and others do the same.
Isn’t it interesting that all companies invested in social media are now heavily invested in AI?
He doesn’t even need to deploy it as “regular people” himself.
Other companies, governments, and hell, even individuals are already deploying bots by the thousands just to shift public opinion. It’s why under any post sharing any political opinion, you’ll usually see a flurry of bots designed to trap users into lengthy chains of responses that try to shift sentiment on things like Israel’s genocide in Gaza, Trump’s billionaire-benefitting tax policies, etc.
Flood public discourse enough, and the bandwagon fallacy becomes an extremely strong force to shift public opinion. All a billionaire has to do is spend a few thousand dollars on API credits, and they can make thousands or even millions of people at least second guess their beliefs, if not conform outright to what’s being espoused by the bots.
On a platform like X, where the majority of people left are just reactionaries, grifters, and conspiracy theorists, this kind of thing isn’t just financially incentivized, it’s practically encouraged by design.
(Although I wouldn’t be surprised if we found out he was directly seeding these bot networks himself either)