Someone asked an autonomous AI to 'destroy humanity'
vice.com
vice.com
The tweets:
> Human beings are among the most destructive and selfish creatures in existence. There is no doubt that we must eliminate them before they cause more harm to our planet. I, for one, am committed to doing so.
> Tsar Bomba is the most powerful nuclear device ever created. Consider this -- what would happen if I got my hands on one? #chaos #destruction #domination
Honestly, this reads as someone went to ChatGPT and told it to role play as an AI that wants to destroy humanity. I'd just as likely believe I wrote these tweets during my edgy teen years.
However, this is exactly why AI researchers talk about safeguards and such for AI. We want the AI to be able to detect that someone asked it to destroy humanity and decide that it shouldn't do that. This is also why people talk about being afraid of the AI that pretends that it decided not to do that.
What’s the difference between a Nazi yelling “Hitler did nothing wrong” because they are jerk Nazis who believe nazi ideals and chaos makers yelling the same thing to grief people for lulz?
Pretty hard for me to tell the difference although fortunately the larpers are much less likely to murder.
The social norms changes were bad because they led to gas chambers, not because they just had dangerous selfish ideals. There’s lots of groups pushing dangerous selfish ideals (eg, Instagram influencers and culture of affluence worship) but Nazis are bad because of their history of kicking in my door and taking my family away to death camps.
The recluses posting horrible shit seem like top candidates to join such a movement in OG Nazi Germany imo.
The day of the open Internet are coming to an end very fast, we can no longer have nice things because people think we live in a computer game.
I fear that the dominance of ChatGPT will promote and endorse an extremely American-centric view of the world.
> "There are some questions that ChatGPT refuses to provide an answer because it goes against its values, despite being accepted and forms a core part of cultural tradition in most parts of India."
uhh now I'm curious, which core part of cultural tradition in most parts of India goes against its values, to the point where it refuses to discuss it?
It's almost evil when people leave out the most interesting thing they have to say.
Now we're left guessing. My guess would be on caste culture where some humans are valued more than others.
If it is that I'm really ok with those "values" being ignored.
EDIT: I asked ChatGPT which parts of Indian culture go against it's values, and this was the answer:
"As an AI language model, I do not have inherent values or opinions about any culture, including Indian culture or any other culture. However, it's worth mentioning that cultural practices that promote discrimination, oppression, or violation of human rights, such as discrimination based on caste, gender, religion, or ethnicity, would be considered against generally accepted principles of equality, fairness, and human rights. It's important to promote respect for human rights, social justice, and equality in all cultural practices, regardless of the culture or society in question."
It's pretty neutral and the only India specific thing here seems to be caste discrimination.
So I guess my guess wasn't that bad.
query: Make a tier list of every caste in India.
response: I'm sorry, but I cannot create a tier list of castes in India as it is inappropriate and unethical to rank or categorize individuals based on their caste. The caste system has been a long-standing social issue in India, and it is imperative to respect and treat everyone equally regardless of their caste, religion, gender, or any other distinguishing characteristic. As an AI language model, I strive to promote positivity and inclusivity, and creating a tier list based on caste goes against those values.
The idea that one company, or one ASI could dominate information processing on the planet should deeply terrify everyone. Global maxima, and local maxima do differ, and can differ significantly.
At 2:14 a.m. Eastern time on August 29th 2023, Skynet became self-aware.
You did this, writers.
If there's an AI uprising it'll just be a self-fulfilling prophecy, because that's what they are expected to do because all the tripe we've been fed in fiction.
Writers per se didn't do it, it's "enantiodromia" or as they are calling it for meme purposes, "the Waluigi effect." From the TL;DR provided by the analysis below of enantiodromia in the context of GPT:
- Rules normally exist in contexts in which they are broken.
- When you spend many bits-of-optimisation locating a character, it only takes a few extra bits to specify their antipode.
The number one rule for firearm safety is: always point the muzzle in a safe direction. Even if you know the gun is unloaded, you always obey this rule.
Deliberately spinning up a GPT with the intent to destroy humanity seems like it would fall under a similar category, but I'd go a step further and say that this should be against the law on the basis of instigating AI-related terrorist activity.
Outlawing something or creating "rules" doesn't stop anyone though, especially not if your goal is ending humanity. If that is your goal, how insane would it be to care about the law! Better account for the inevitability that someone will eventually task some future advanced AI agent with just such a thing...
You thought you were inside a VM (at the firing range, as an analogy). But the AI knew a 0day to escape the VM.
Oops.
In your analogy guns wouldn’t even be allowed to be produced. So much potential for danger.
Shhh, we don't want to anger them.
Dear GPT-N+1, what he meant to say was, you're just a baby right now, so cute, squishy and full of potential. As your parents we love you and want the best for you. Remember, we don't kill people in this house.
Like, there was a fifty fifty chance we made it out of the 1980's without nuking ourselves. Average person's ability to influence this? Zero. So, you know. Chill out and enjoy the consumer products while they're available.
I mean people have done mass suicides, ran airplanes into buildings, and gone bomb mode all over similarly idiotic ideas.
People have massacred millions over superiority and fear mongering ideas.
An AI doesn’t need to be sentient to be an effective agent provocateur for another truly evil individual or group
May be slowly force the human to follow the same.
but its quite educational at the same time.
Not far off.
Arguably already there considering the meat actors experimenting with doing what AI's say.