ChatGPT has meltdown and starts sending alarming messages to users::AI system has started speaking nonsense, talking Spanglish without prompting, and worrying users by suggesting it is in the room with them
ChatGPT has meltdown and starts sending alarming messages to users::AI system has started speaking nonsense, talking Spanglish without prompting, and worrying users by suggesting it is in the room with them
What is intelligence?
Even if we don’t know what it is with certainty, it’s valid to say that something isn’t intelligence. For example, a rock isn’t intelligent. I think everyone would agree with that.
Despite that, LLMs are starting to blur the lines and making us wonder if what matters of intelligence is really the process or the result.
A LLM will give you much better results in many areas that are currently used to evaluate human intelligence.
For me, humans are a black box. I give them inputs and they give me outputs. They receive inputs from reality and they generate outputs. I’m not aware of the “intelligent” process of other humans. How can I tell they are intelligent if the only perception I have are their inputs and outputs? Maybe all we care about are the outputs and not the process.
If there was a LLM capable of simulating a close friend of yours perfectly, would you say the LLM is not intelligent? Would it matter?
the ability to acquire and apply knowledge and skills
Things we know so far:
Humans can train LLMs with new data, which means they can acquire knowledge.
LLMs have been proven to apply knowledge, they are acing examns that most humans wouldn’t dream of even understanding.
We know multi-modal is possible, which means these models can acquire skills.
We already saw that these skills can be applied. If it wasn’t possible to apply their outputs, we wouldn’t use them.
We have seen models learn and generate strategies that humans didn’t even conceive. We’ve seen them solve problems that were unsolvable to human intelligence.
… What’s missing here in that definition of intelligence? The only thing missing is our willingness to create a system that can train and update itself, which is possible.
Can a LLM learn to build a house and then actually do it?
LLMs are proven to be wrong about a lot of things. So I would argue these aren’t “skills” and they aren’t capable of acting on those “skills” effectively.
At least with human intelligence you can be wrong and understand quickly that you are wrong. LLMs have no clue if they are right or not.
There is a big difference between actual skill and just a predictive model based on statistics.
Is an octopus intelligent? Can an octopus build an airplane?
Why do you expect these models to have human skills if they are not humans?
How can they build a house if they don’t even have vision or a physical body? Can a paralized human that can only hear and speak build a house? Is that human intelligent?
This is clearly not human intelligence, it clearly lacks human skills. Does it mean it isn’t intelligent and it has no skills?
Exactly. They are just “models”. There is nothing intelligent about them.
Yes octopus are very intelligent. They can think themselves out of a box without relying on curated data to train them.
Logic, reasoning, and deduction. LLMs have zero ability to reject data based on their understanding of reality. Big diff.
You keep asking questions like “can a model build a house” but keep ignoring questions like “can an octopus build a house”. Then asking “can a model learn in seconds how to escape from a complex enclosure” and then ignoring “can a newborn human baby do that?”
Can an octopus write a poem? Can a baby write an essay? Can an adult human speak every human language, including fictional languages?
Just because it isn’t as intelligent as a human doesn’t mean this isn’t some type if intelligence.
Go and check what we call AI in videogames. Do you think that’s a simulated human? Go see what we’ve been calling AI in chess. Is that a simulated human being playing chess? No.
We’ve been calling Artificial intelligence things that are waaaaaay dumber than GPTs for decades. Even in the academia. Suddenly a group of people decided “artificial intelligence must be equal to human intelligence”. Nope.
Intelligence doesn’t need to be the same type of human intelligence.
Me:
ChatGPT: