humans have much to learn from robotkind
19
37
12
248
it's all about the prelude before the conversation. You need to tell it what the AI is and is not capable. It's not trying to be right, it's trying to complete what it thinks the AI would do :)
21
108
50
757
I wonder if the AI would be better at math if you told it to show it's work
1
5
1
61
Seems to work
11
48
29
308
Teaching GPT-3 to do a brute force 'for loop' checking answers also seems to work

12:12 PM · Jul 17, 2020

9
44
13
220
You’re unable to view this Tweet because this account owner limits who can view their Tweets.
It feels RNNish
1
0
0
5
The AI yelling “first try” on his second try is definite proof that it's becoming human.
0
8
0
90
Unrelated but, this is ridiculously cute the way it communicates. Would die to protect it
1
0
2
28
In 2020 people developed an AI which needs a sense of purpose and positive emotional background to solve math.
0
4
0
37
Unbelievable. What was your starting prompt?? In my attempts it tends to narrate the result of the dialogue instead of the answer to the question (e.g. "You ask 'what is a good approximation of pi?'" --> "She gives you an answer that's good enough to use on a test."
2
0
0
3
Mine started strong but then...
1
0
0
3
Hold on a second. Is this all real? I am not nearly as impressed by the function composition or arithmetic as by the metacognition and question asking. So the story-Socratic format is how to get interactivity? Really? How many trials is this? Did you really not edit this?
1
1
0
8
+1. I want to believe, but I don't want my heart broken... is this really happening?
1
0
0
1