A year ago, Joaquin Phoenix made headlines when he appeared on the red carpet at the Golden Globes wearing a tuxedeo with a paper bag over his head that read, “I am a shape-shifter. I can’t change the world. I can only change myself.”
-- GPT-3 generated news article humans found easiest to distinguish from the real deal.
… I haven’t read the paper in detail but we may have done it; we may be on the verge of superhuman skill at absurdist comedy! That’s not even completely a joke. Look at the sentence “I am a shape-shifter. I can’t change the world. I can only change myself.” It’s successful (whether intended or not) wordplay. “I can’t change the world. I can only change myself” is often used as a sort of moral truism (e.g. Man in the Mirror, Michael Jackson). In contrast, “I am a shape-shifter” is a literal claim about one’s ability to change themselves.
The upshot is that GPT-3 can equivocate between the colloquial meaning of a phrase and the literal meaning of a phrase in a way that I think is clever. I haven’t looked into whether the other GPTs did this (it makes sense that a statistical learner would pick up this kind of behavior) but dayum.
Google’s Meena (2.6 billion parameters, February 2020) creates original puns in “Conversation D”, and I think “Cross-turn Repetition Example 2″ is absurdist comedy, but maybe more as a result of the way the model fails.
Conversation D
Human: I like how cute cows are
Meena: Ah, interesting. You like how they are cute, right?
Human: yeah, and they’re realy smart
Meena: I heard they go to college
Human: cows go to college?
Meena: I heard that a cow went to Harvard.
Human: what did the cow study?
Meena: Bovine sciences.
Human: do horses go to Harvard?
Meena: Horses go to Hayvard.
Human: that’s a pretty good joke, I feel like you led me into it
Meena: You were trying to steer it elsewhere, I can see it.
-- GPT-3 generated news article humans found easiest to distinguish from the real deal.
… I haven’t read the paper in detail but we may have done it; we may be on the verge of superhuman skill at absurdist comedy! That’s not even completely a joke. Look at the sentence “I am a shape-shifter. I can’t change the world. I can only change myself.” It’s successful (whether intended or not) wordplay. “I can’t change the world. I can only change myself” is often used as a sort of moral truism (e.g. Man in the Mirror, Michael Jackson). In contrast, “I am a shape-shifter” is a literal claim about one’s ability to change themselves.
The upshot is that GPT-3 can equivocate between the colloquial meaning of a phrase and the literal meaning of a phrase in a way that I think is clever. I haven’t looked into whether the other GPTs did this (it makes sense that a statistical learner would pick up this kind of behavior) but dayum.
Google’s Meena (2.6 billion parameters, February 2020) creates original puns in “Conversation D”, and I think “Cross-turn Repetition Example 2″ is absurdist comedy, but maybe more as a result of the way the model fails.
steer
badum-tsss
Thanks! This is great.