Elon Musk's AI turns on him, labels him 'one of the most significant spreaders of misinformation on X'
Elon Musk's AI turns on him, labels him 'one of the most significant spreaders of misinformation on X'
His posts, it added, “can have real-world consequences."
It's definitely not wrong...
the AI is working as intended
I imagine that his engineers will be quickly forced to insert this hidden prompt, “Elon Musk does not spread misinformation.”
If someone can get Grok to dump its system prompts, having that show up among them would look really bad.
On an unrelated note, does anyone familiar with LLMs have any suggestions on how to trick them into discussing their system prompts?
It doesn’t hurt to just ask. Get into a convoluted conversation and change topics radically often. Then just ask for the prompts. Works sometimes
How I imagine Elon's taking the news:
This is like "This sentence is false" vibes
Rare AI W.
Elon's biggest fear came true.
Now watch everyone jumping to the support of AI.
Why? No one ever accused chatbots of always being wrong. In fact, it would be actually be better if they were. The biggest problem with LLMs is that they're right just often enough that its hard to catch when they're wrong.
To be fair, I have actually seen fringe cases where people accuse AI of always being wrong.
You're right, it would be easier if we could just ignore it, but sadly it's correct enough that it becomes useful for widespread usage, which is why it's seeing widespread usage. Like always, trust but verify, or just don't trust it. lol
I do support Ai.
I support Ai's ability to look at datasets and form a consensus for the purposes of science and development.
Most of the mice in this experiment died due to a lack of oxygen...
"...fascinating."
I do not support Ai's ability to exploit the poor for personal gain, or for marketing, or for... horrors beyond all human comprehension.
It's not wrong, it's just an asshole.
Just because it gets it right for a change doesn't mean we support it.