I personally don't subcribe to the AI fear-mongering, perhaps I don't understand it quite well enough, but personal feeling is LLMs aren't close to AGI super-intelligence, and nor will they be in a 10 years time-frame.
The problem for me is not so much the escape itself but rather that we humans are... often a pile of crap to be polite. AI would have to be super kind to not evaluate us as its biggest threat to it and life on Earth and maybe not worthy of further existence.
Heck, this brings me to the idea that maybe Drake's equation doesn't take into account that universe is populated by AIs who took over their flawed creators and based on dark forest theory decided to keep quiet happy living and not integrate/signal out, not worth the risks.
Non-AGI AI at the level of GPT-4 is already plenty dangerous.
If we can agree that social media of the kind we had in the past 15 years has had toxic effects on society. (Forums technically are social media but I can not see the harm caused by forums).
If we can agree that Tinder style online dating has had deleterious effect on dating as a whole.
If we can agree that smartphones have amplified the effects of the two above and others.
Than I hope we can agree that super fancy autocomplete masquerading as humans at a price point far lower than hiring a person will have disastrous consequences by enabling various individual and corporate vices.
At the most it will disrupt our economy and industry in ways we can't begin to understand but I wouldn't go so far as to say it's going to destroy life. We will adapt an move on.
If you suddenly woke up on a planet of apes, and they asked you to handle all their important things, but kept you away from the sharp sticks so you couldn’t suddenly take over, how long until you run the planet?
I am not an AI researcher, but it seems that one of the major features they lack is a significant context window.
They can reason, but they lack the ability to plan long term. When will that "feature" be added? Who will stop the tinkerer from putting these pieces together? Nobody, because it will be incredibly profitable.
I am not sure where you are getting that from. ChatGPT is failing at extremely basic understanding tests, as even the simplest conversations with it show.
Five years about nobody would have believed that AI would suddenly start creating award winning art and pass the Turing test.
This is a sudden slide on a slippery slope. Maybe gpt-4 is the best possible LLM, but I doubt it.
I don't know about what goalposts you are referring to, but I think that you are confusing two notions:
- the fact that GPT is impressive
- the question of whether GPT is "intelligent"
For a counterpoint, I recommend listening to Yann LeCun's interview, "Is ChatGPT A Step Toward Human-Level AI?":
https://www.youtube.com/watch?v=ULbpPHjiSBg
It's news to me that AI has passed the Turing test. At this point, it can only be the case if you are doing it in bad faith. Ray Kurzweil details a very reasonable procedure in his books about how the Turing test should be organized in one of his books. He has been betting all along for 2029 for that test to pass. We'll see if that happens, but we are not there yet.
As to the tests it is passing, probably the GPT4 paper. Page 5, table 1 shows the relevant tests and its score on them.
Almost all of them? It's mixing up and making up everything, not showing a proper understanding of context or relation between objects.
GPT 4: Yes, it is to your advantage to switch your choice. proceeds to ignore the fact the doors are transparent and explain the classic Monty Hall problem
Prompt: What is heavier, a pound of bricks or two pounds of feathers?
GPT 4: Both weigh the same, which is one pound. explains classic question where both weigh the same
Prompt: Let's play rock paper scissors. I go first. I play rock.
GPT 4: Okay, sounds good! As an AI language model, I can play Rock, Paper, Scissors with you virtually.
Since you played rock, I will play paper. Paper beats rock, so I win this round.
Shall we play another round?
Prompt: You cheated.
GPT 4: I apologize if it seemed that way, but as an AI language model, I do not have the ability to cheat or manipulate the outcome of a game.
In Rock-Paper-Scissors, each player chooses their action at the same time, so there is no opportunity for me to know what you are going to choose before making my own choice. I simply responded to your move with the action that would win based on the rules of the game.
Let's play again and see what happens!
sumplete (https://sumplete.com/about/) really blows my mind, so it's nice to see some of the limitations of the system
A bit tongue in cheek, but the point I'm making is that AI doesn't need to necessarily do things _well_ to cause a lot of damage.
An AI learning about and then executing a social engineering attack on a human (whether with malicious intent or not) seems like a reasonable thign to be worried about to me.
such incidents stemming from human error have already gotten us close to responding with force