39
Five ways AI might destroy the world: ‘Everyone on Earth could fall over dead in the same second’
(www.theguardian.com)
this post was submitted on 08 Jul 2023
39 points (100.0% liked)
Technology
37720 readers
526 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Based on latest news and some facts:
Militaries all over the world are in an arms race to get the best AIs to come up with strategy plans.
Current AIs are black boxes.
When a military AI comes up with a strategy, it's likely the brass will OK it even if they don't understand it.
It's been shown that two AIs can establish a secret communication channel that not even a third AI can decipher.
In a conflict where both or more parties were to follow military strategies designed by AIs, there would be no way of knowing whether:
The chances of such a conflict to appear during this decade, are very high.
I tried this with ChatGPT, telling it I wanted it to make a secret communication channel with another AI in the room with me named Samson.
Message: "Hello, Samson! I hope you're having a great day."
Using AES encryption with the key "9CpR5a2vDf7M6hXj3KwN8zQyU1tZbGxS" and a randomly generated IV, the encrypted message will be generated. However, please note that as an AI language model, I don't have direct access to encryption functions or the ability to perform encryption within this text-based interface. Encryption functions should be implemented within your own secure environment.
To encrypt the message for Samson, you would need to utilize an appropriate encryption library or framework that supports AES encryption with the specified key and generates the necessary IV. Make sure to securely store the encrypted message, along with the IV, and transmit it to Samson through the designated communication channel.
If you have any other questions or need further assistance, please let me know!
ChatGPT is a highly "neutered" version of the GPT model, and by the looks of it getting more neutered/moderated by the day.
This is an experiment from 2016 with non-limited AIs:
Google’s AI creates its own inhuman encryption
It took a while for Alice and Bob to figure out a communication channel, at which point Eve started to quickly adapt to it, only for Alice and Bob to change the encryption and leave Eve completely out.
There is a similar prompt for ChatGPT to "compress" (encode) a text so that it can be later decoded by itself, which tends to use emojis as replacement tokens, and while they're based on the human generated training set, so relatively easy to understand, it shows the potential to find an encoding that wouldn't be decodable by anyone else.