It seems that this tendency to "hallucinate" and, at the same time not know when it's wrong, is not at all easy to correct; it's baked into the way this kind of neural network works. We'll see how open.ai and other AI developers tackle it.
Much like ChatGPT, linguist and public intellectual Noam Chomsky may be right or he may be wrong, but he's always authoritative. You can read his very interesting take on ChatGPT and AI's limitations here.
How flexible or creative is ChatGPT? Isn't it just regurgitating what it read during its training?
Creativity is subjective, so I'll again suggest that readers try out ChatGPT and judge for themselves. One point worth noting is that ChatGPT works with an adjustable variable called "temperature" that determines how rigidly or flexibly it chooses words or phrases. A higher "temperature" setting produces more flexibility in the choices it makes. This may not represent creativity, but it does mean that ChatGPT can and does produce different responses to the same prompt.
As a test, I first asked it to briefly describe the Big Bang theory. I won't quote its answer here, but it was a clear and accurate description of the basics of the theory presented at the level of a popular science piece. I then asked it how it would present the Big Bang theory to a class of ten year olds. Here's its response:
Sure, I'd be happy to explain the Big Bang to 10-year-old children in a way that's easy to understand!
The Big Bang is like a giant explosion that happened a really, really long time ago - so long ago that it's hard for us to even imagine! This explosion created everything in the universe, like the stars, planets, and galaxies.
Imagine if you blew up a balloon and kept blowing it up until it got really, really big - that's kind of like what happened with the universe! It started out really small and then expanded and got bigger and bigger until it was as big as it is now.
Other people have asked ChatGPT to write various kinds of poetry, including Shakespearean sonnets. You can find an interesting piece on "engineering" a poem, and the resulting ChatGPT poem here. It's poured out so many pulp science fiction stories that sci-fi magazines have banned them.
I happen to like haiku - three-line, 17-syllable poems often inspired by a natural event at a particular moment and suggesting an emotional reaction. Here one by ChatGPT, responding to my prompt to write a haiku inspired by seeing a single heron standing in a field in autumn:
Heron stands so still.
Autumn breeze rustles dry grass.
Solitude, her fate.
I was impressed enough by this example that I asked ChatGPT to write a haiku with a similar feeling tone about an AI. Here's its response:
In circuits she dwells.
No touch, no voice, no embrace.
Next Page 1 | 2 | 3 | 4 | 5 | 6 | 7
(Note: You can view every article as one long page if you sign up as an Advocate Member, or higher).
2
2
1
