"When OpenAI announced the release of GPT-5 this month, the company boasted about how it could supposedly produce "resonant writing with literary depth and rhythm." In a lengthy post on his personal blog, University of Munich research fellow Christoph Heilig put that bold assertion to the test. What he found was bizarre: the model easily spits out material that sounds literary and sophisticated, but on closer inspection it's often flowery and incoherent gibberish that makes no sense at all."
""The red recording light promised truth; the coffee beside it had already stamped it with a brown ring on the console," it spat out. "I adjusted the pop filter, as if I wanted to politely count the German language's teeth." At a quick glance, it looks writerly enough. But stop and think it through. What does it mean to count the German language's teeth, and what does doing so have to do with a microphone's pop filter?"
"In another test, Heilig asked GPT-5 for a new spin on the passage from Lewis Carroll's "Through The Looking-Glass" in which Alice is told that she'll always have to wait for the promised " jam tomorrow." In response, the LLM composed something similarly baffling. "She says: 'In a moment.' In a moment. 'In a moment' is a dress without buttons," GPT-5 wrote."
GPT-5 produces prose that mimics literary tone and rhythm while frequently lacking coherent meaning or internal logic. The model can generate striking images and metaphors that read as sophisticated at first glance but collapse under scrutiny into incongruent or nonsensical statements. Examples include a podcast opening that links a pop filter to "count[ing] the German language's teeth" and a Lewis Carroll riff equating "in a moment" to a buttonless dress. The outputs exhibit surface-level authorial voice without consistent semantic connections, exposing limitations in the model's claimed literary depth.
Read at Futurism
Unable to calculate read time
Collection
[
|
...
]