Ha!
nature journal wrote:As AI-generated text continues to evolve, distinguishing it from human-authored content has become
increasingly difficult. This study examined whether non-expert readers could reliably differentiate
between AI-generated poems and those written by well-known human poets. We conducted two
experiments with non-expert poetry readers and found that participants performed below chance
levels in identifying AI-generated poems (46.6% accuracy, χ2(1, N=16,340)=75.13, p<0.0001).
Notably, participants were more likely to judge AI-generated poems as human-authored than actual
human-authored poems (χ2(2, N=16,340)=247.04, p<0.0001). We found that AI-generated poems
were rated more favorably in qualities such as rhythm and beauty, and that this contributed to their
mistaken identification as human-authored. Our findings suggest that participants employed shared
yet flawed heuristics to differentiate AI from human poetry: the simplicity of AI-generated poems may
be easier for non-experts to understand, leading them to prefer AI-generated poetry and misinterpret
the complexity of human poems as incoherence generated by AI....
Here, we extend prior work by showing that AI-generated poetry has reached the level of AI-generated
images in non-expert assessments: across multiple eras and genres of poetry, non-expert participants cannot
distinguish human-written poetry from poems generated by AI without human intervention or specialized
fine-tuning. Like AI-generated paintings and faces, AI-generated poems are now “more human than human”:
we find that participants are more likely to judge that AI-generated poems are human-authored, compared to
actual human-authored poems. Contrary to previous studies, we also find that participants rate AI-generated
poems more highly than human-written poems across several qualitative dimensions. However, we confirm
earlier findings that participants evaluate poems more negatively when told that the poem is generated by AI, as
opposed to being told the poem is human-written.
answer in whiteI speak of love that comes to mind:
The moon is faithful, although blind;
She moves in thought she cannot speak.
Perfect care has made her bleak.
I never dreamed the sea so deep,
The earth so dark; so long my sleep,
I have become another child.
I wake to see the world go wild.
I never liked Ginsberg.hbiden@onlyfans.com wrote: Thu Feb 06, 2025 11:43 amnature journal wrote:As AI-generated text continues to evolve, distinguishing it from human-authored content has become
increasingly difficult. This study examined whether non-expert readers could reliably differentiate
between AI-generated poems and those written by well-known human poets. We conducted two
experiments with non-expert poetry readers and found that participants performed below chance
levels in identifying AI-generated poems (46.6% accuracy, χ2(1, N=16,340)=75.13, p<0.0001).
Notably, participants were more likely to judge AI-generated poems as human-authored than actual
human-authored poems (χ2(2, N=16,340)=247.04, p<0.0001). We found that AI-generated poems
were rated more favorably in qualities such as rhythm and beauty, and that this contributed to their
mistaken identification as human-authored. Our findings suggest that participants employed shared
yet flawed heuristics to differentiate AI from human poetry: the simplicity of AI-generated poems may
be easier for non-experts to understand, leading them to prefer AI-generated poetry and misinterpret
the complexity of human poems as incoherence generated by AI....
Here, we extend prior work by showing that AI-generated poetry has reached the level of AI-generated
images in non-expert assessments: across multiple eras and genres of poetry, non-expert participants cannot
distinguish human-written poetry from poems generated by AI without human intervention or specialized
fine-tuning. Like AI-generated paintings and faces, AI-generated poems are now “more human than human”:
we find that participants are more likely to judge that AI-generated poems are human-authored, compared to
actual human-authored poems. Contrary to previous studies, we also find that participants rate AI-generated
poems more highly than human-written poems across several qualitative dimensions. However, we confirm
earlier findings that participants evaluate poems more negatively when told that the poem is generated by AI, as
opposed to being told the poem is human-written.
Al Ginsberg or A.I. Ginsberg? Test yourself.answer in whiteI speak of love that comes to mind:
The moon is faithful, although blind;
She moves in thought she cannot speak.
Perfect care has made her bleak.
I never dreamed the sea so deep,
The earth so dark; so long my sleep,
I have become another child.
I wake to see the world go wild.
real ginsberg.