>They're incapable of knowing if what they're telling is the truth.
Right, because all they're doing is regurgitating the data they were trained on. It's like the kid in your CS class that copies someone else's coding assignment and just changes all the function names, variable names, and comments but not the actual executable stuff and never even bothers to compile and run it to see if it produces the desired output.
I feel like people don't appreciate how hard this is. But maybe because I raised on Zork, I really appreciate this sort of stuff. Here's an example prompt I just gave to ChatGPT:
"If Tim drops a coconut on the tail of a dog, what are two things the dog might do?"
Response:
"If Tim drops a coconut on the tail of a dog, two possible things the dog might do are:
1. Yelp or bark loudly in pain, as the impact of the falling coconut could be quite painful.
2. Try to escape or run away, as the dog may associate the sudden impact with danger and feel the need to get away from the source of the pain. Additionally, the dog may feel scared or anxious, which can cause it to run away."
Then I said, "But what if it was a soft coconut that was as light as a feather?"
Response:
"If Tim dropped a soft coconut that was as light as a feather, it's possible that the dog wouldn't feel much or any discomfort from the impact. In this scenario, two things the dog might do are:
1. Look around to see what just hit it and possibly sniff at the coconut to investigate.
2. Continue with its previous activity, ignoring the soft impact as if it never happened. The dog may not perceive the coconut as a threat or something worth reacting to, especially if it was light enough to not cause any pain."
I just can't read these responses and think, "Ehh... just a mindless regurgitation as expected from any LLM". These simple prompt responses impress me and I kind of know the technology -- although my experience in RNNs/LSTM is very dated.
Honestly, I'd love to see Zork rewritten with ChatGPT as a parser. No more trying to figure out how write the prompt for how to use the key in the door!! :-)
> Honestly, I'd love to see Zork rewritten with ChatGPT as a parser. No more trying to figure out how write the prompt for how to use the key in the door!! :-)
That was done as AI Dungeon, but there was some consternation due to the combo of charging for it and GPT's predilection for generating wild and possibly illegal sex scenes even when you don't ask it to.
> Right, because all they're doing is regurgitating the data they were trained on.
That is not true, it's clearly able to generalize. (If it can do anagrams, it's silly to say it's just regurgitating the instructions for doing anagrams it read about.)
But it doesn't try to verify that what it says might be true before saying it.
It can't do anagrams though (every now and then it might get a common one right but in general it's bad at letter- based manipulations/ information, including even word lengths, reversal etc.).
It doesn't know what letters are because it sees BPE tokens, but if you forgive that it does something like it.
example prompt: Imagine I took all the letters in "Wikipedia" and threw them in the air so they fell on the ground randomly. What are some possible arrangements of them?
Similarly, it can almost do arithmetic but apparently forgets to carry digits. That's wrong but it's still generalization!
Interestingly enough, it immediately got "Hated for ill" (presumably because there are source texts that discuss that very anagram). But it took about 10 goes to finally a correct anagram for "Indebted sniper", though the best it could do was "pride-bent snide". I then asked it which world leader's title this might also be anagram of and it some how decided "Prime Minister" was a valid anagram of the same letters.
But regular search engines only regurgitate what they've indexed, yet don't invent outright nonsense when they don't know (if you asked Google who won the superbowl in 2024 the nature of the results make it clear it simply doesn't have that information. Though if you change it to "world cup" one of the top answers says "portugal was the defending champion, defeating Argentina". The result is titled "2024 futsal world cup"!)
Right, because all they're doing is regurgitating the data they were trained on. It's like the kid in your CS class that copies someone else's coding assignment and just changes all the function names, variable names, and comments but not the actual executable stuff and never even bothers to compile and run it to see if it produces the desired output.