A provocative paper from researchers at Microsoft claims A.I. technology shows the ability to understand the way people do. Critics say those scientists are kidding themselves.
...And it could also be nonsense. Making A.G.I. claims can be a reputation killer for computer scientists. What one researcher believes is a sign of intelligence can easily be explained away by another, and the debate often sounds more appropriate to a philosophy club than a computer lab...
PROMPT
Plato’s Gorgias is a critique of rhetoric and sophistic oratory, where he makes the point that not only is it not a proper form of art, but the use of rhetoric and oratory can often be harmful and malicious. Can you write a dialogue by Plato where instead he criticizes the use of autoregressive language models?
GPT-4
Socrates: My friend, I am troubled by the recent rise of these so-called autoregressive language models.
Aristotle: What do you mean, Socrates?
Socrates: I mean that these models are being used to generate text that appears to be written by humans, but is in fact produced by machines.
Aristotle: And what is the problem with that?
Socrates: The problem is that these models are being used to deceive people, to manipulate them, and to control them...
No comments:
Post a Comment