Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:
I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
It seems to me that you misunderstand what artificial intelligence means. AI doesn’t necessitate thought or sentience. If a computer can perform a complex task that is indistinguishable from the work of a human, it will be considered intelligent.
You may consider the classic turing test, which doesn’t question why a computer program answers the way it does, only that it is indiscernable from a human response.
You may also consider this quote from John McCarthy on the topic:
There’s more on this topic by IBM here.
You may also consider a few extra definitions:
Yep, all those definitions are correct and corroborate what the user above said. An LLM does not learn like an animal learns. They aren’t intelligent. They only reproduce patterns similar to human speech. These aren’t the same thing. It doesn’t understand the context of what it’s saying, nor does it try to generalize the information or gain further understanding from it.
It may pass the Turing test, but that’s neither a necessary nor sufficient condition for intelligence. It is just a useful metric.
LLMs are expert systems, who’s expertise is making believable and coherent sentences. They can “learn” to be better at their expert task, but they cannot generalise into other tasks.
LLMs are no more ai than the enemies in doom were.
The enemies in Doom actually do some pretty dumb things, like letting you force them to stop moving.
While John McCarthy and other sources offer valuable definitions, none of them fully encompass the qualities that make an entity not just “clever” but genuinely intelligent in the way humans are: the ability for abstract thinking, problem-solving, emotional understanding, and self-awareness.
If we accept the idea that any computer performing a task indistinguishable from a human is “intelligent,” then we’d also have to concede that simple calculators are intelligent because they perform arithmetic as accurately as a human mathematician. This reduces the concept of intelligence to mere task performance, diluting its complexity and richness.
By the same logic, a wind-up toy that mimics animal movement would be “intelligent” because it performs a task—walking—that in another context, i.e., a living creature, is considered a sign of basic intelligence. Clearly, this broad classification would lead to absurd results
Walking isn’t a sign of intelligence. Starfish walk, using hundreds to thousands of feet uder each arm, and sometimes the arms themselves. Sea pigs also walk, and neither have a brain.
Besides, you’re strawmanning their definition;
is very different from
A good calculator can compute arithmetic better than a mathematician, but it cannot even parse the work of a high school student. Wolfram Alpha on the other hand gets pretty close.
A wind up toy can propel itself using as few as one appendage, but fails at actually traversing anything. Some machines with more legs can amble across some terrain, but are still beaten by a headless chicken. Meaningful travel needs a much more complex system of object avoidance and leg positioning, which smells more like AI.
The way AI is often used isn’t “do a task that a human has done”, but “replace the need for a human, or at least a specialist human”. Chess AI replaces the need for a second player, as do most game AIs. AI assistants replace much of the need for, well, assistants and underwriters. Auto-pilots replace the need for constantly engaged pilots, allowing bathroom breaks and rest.
Meanwhile, you can’t use a calculator without already knowing how to math, and even GPS guided tractors need a human to set up the route. These things aren’t intelligent in any way; they’re incapable of changing behavior to fit different situations, and can’t deploy themselves.