Si tratta di questo articolo:
https://www.nytimes.com/2023/03/08/opinion/noam-chomsky-chatgpt-ai.html
(mi scuso qualora se ne fosse già discusso in lista)
Ne stavo discutendo con colleghi di vari paesi in un'altra
mailing list e in risposta ad alcune critiche fatte all'articolo
ho scritto quanto riporto sotto (scusatemi se lo lascio in inglese
ma siccome coinvolge l'uso di ChatGPT nell'analisi di un testo in
inglese traducendolo diventava un'altra cosa)
...
I find your viewpoint highly interesting, even if I somehow
disagree on some of your criticism to Chomsky's article.
I find an analogy between the way ChatGPT learned to master the
language in comparison to human beings and how Alpha Zero learned
to master board games in comparison to human beings.
The deep-learning based approach exploited in both cases (almost)
all available data, either through their availability on the
Internet (in the case of the language) or through sophisticated
systematic search through the strategy space (in the case of board
games).
Human beings become master (in both fields) leveraging a much
smaller information space: the number of examples a child is
exposed to while learning language is, just by considering time
and space constraints, much smaller than what ChatGPT used. I do
not know of any estimation of this (which would be an interesting
thing to do) but I would say the size is inferior of some orders
of magnitude (which to me implies the "language learning
algorithm" inside human brain is exponentially more efficient then
those used in DL - but that's a different story).
Moreover human beings know the "meaning" of their action and are
aware of the fact that they know such meaning.
(See the note at the end supporting my statements.)
This appears to me to be an important difference between the two
approaches and I think is the reason why Chomsky wrote that
ChatGTP is not going to teach us anything useful about how human
beings learn and use language.
One more interesting discussion of the Chomsky viewpoint, this
time defending it, I suggest (in case you've not already read it)
is the piece of Gary Marcus
https://garymarcus.substack.com/p/caricaturing-noam-chomsky
Best, Enrico
NOTE: To test my statements I asked ChatGPT to analyse a paragraph
of my mail. You can read the prompt and the answer further below.
The answer is at best confusing.
ChatGPT fails to identify the text has 2 sentences and not just 1.
It does a wrong analysis of the first sentence, which contain two
main clauses and not one main and one subordinate.
That's particularly interesting since right after the wrong
analysis it "explains" that "a main clause is an independent
clause that stands alone as a complete sentence". So, it writes
that it "knows" what a main clause is right after having shown it
doesn't know.
And the rest contains a number of additional errors.
So, even if the examples ChatGPT has been exposed to surely
contain many descriptions of grammar rules, it has not been able
to get any understanding of them. A secondary high school student,
having received much less data and much less training is able to
do a much better job.
CVD :-)
PROMPT
Please perform the analysis of clause and sentence structure of
the text enclosed below between «»:
«Human beings become master (in both fields) leveraging a much
smaller information space: the number of examples a child is
exposed to while learning language is, just by considering time
and space constraints, much smaller than what ChatGPT used. I do
not know of any estimation of this (which would be an interesting
thing to do) but I would say the size is inferior of some orders
of magnitude (which to me implies the "language learning
algorithm" inside human brain is exponentially more efficient then
those used in DL - but that's a different story).»
ANSWER (ChatGPT release of Feb.13 - tested on Mar.14th)
The text contains one sentence:
"Human beings become master (in both fields) leveraging a much
smaller information space: the number of examples a child is
exposed to while learning language is, just by considering time
and space constraints, much smaller than what ChatGPT used. I do
not know of any estimation of this (which would be an interesting
thing to do) but I would say the size is inferior of some orders
of magnitude (which to me implies the "language learning
algorithm" inside human brain is exponentially more efficient then
those used in DL - but that's a different story)."
The sentence contains two clauses:
Main clause: "Human beings become master leveraging a much
smaller information space"
Subordinate clause: "the number of examples a child is exposed
to while learning language is, just by considering time and space
constraints, much smaller than what ChatGPT used"
The main clause is an independent clause that stands alone as a
complete sentence. It contains a subject ("human beings") and a
predicate ("become master leveraging a much smaller information
space").
The subordinate clause is a dependent clause that cannot stand
alone as a complete sentence. It provides additional information
to the main clause by describing the size of the information space
that humans use to become masters in both fields. The subordinate
clause contains a subject ("the number of examples a child is
exposed to while learning language") and a predicate ("is much
smaller than what ChatGPT used"). The phrase "just by considering
time and space constraints" acts as an adverbial modifier that
further clarifies the subordinate clause.
The text also contains two embedded clauses:
"which would be an interesting thing to do" is an embedded
clause that acts as an object of the verb "know" in the main
clause.
"which to me implies the 'language learning algorithm' inside
human brain is exponentially more efficient then those used in DL
- but that's a different story" is an embedded clause that acts as
the subject of the verb "is" in the subordinate clause.
Additionally, the text contains a parenthetical remark: "but
that's a different story," which is not syntactically connected to
the rest of the sentence.
END OF CHATGPT ANSWER