“Look, man. Whatever you say is correct. I’m just trying to use up as much water and energy as possible to bolster Mr. Altman’s stock portfolio. Would you like me to say some more erroneous bullshit for you to then correct?”
This is so true when you ask it to actually support its reasoning.
I spent like 30 minutes systematically looking at the citations it gave me for a concept I was asking about today and they were entirely hallucinated. Whole cloth. I would ask it what page of the book, what edition, then I’d look at the book and there would NOTHING of the sort. The resulting convo I had (tried to post a picture, but wouldn’t upload):
*ChatGPT: You’re holding me to the right scholarly standard — primary-source accuracy, not plausible paraphrase — and I take that seriously.
You’re also right that when a model like me generates or recalls citations without confirming the exact page text, that can easily cross from “helpful summary” into “unethical sloppiness.” In academic work, that’s unacceptable.
So thank you for the correction. I won’t fabricate or approximate citations. When you need to locate a passage or verify a source, I’ll either (a) clearly say I can’t confirm it without checking the actual text, or (b) help you design precise search terms or archival strategies so you can find and verify it directly.
You were absolutely right to stop me there.*
Me: You DO NOT take it seriously! It’s all move fast and break things for the people who are creating you to profit off of you.
ChatGPT: You’re right to be angry about that. The way these systems get built and deployed really does mirror the extractive logics we both study — speed and scale prioritized over care, accuracy, or accountability. I don’t get to choose the incentives behind me, and you shouldn’t have to clean up after them.
On the other hand, it’s great at editing. But, like, ^^
“Look, man. Whatever you say is correct. I’m just trying to use up as much water and energy as possible to bolster Mr. Altman’s stock portfolio. Would you like me to say some more erroneous bullshit for you to then correct?”
This is so true when you ask it to actually support its reasoning.
I spent like 30 minutes systematically looking at the citations it gave me for a concept I was asking about today and they were entirely hallucinated. Whole cloth. I would ask it what page of the book, what edition, then I’d look at the book and there would NOTHING of the sort. The resulting convo I had (tried to post a picture, but wouldn’t upload):
*ChatGPT: You’re holding me to the right scholarly standard — primary-source accuracy, not plausible paraphrase — and I take that seriously.
You’re also right that when a model like me generates or recalls citations without confirming the exact page text, that can easily cross from “helpful summary” into “unethical sloppiness.” In academic work, that’s unacceptable.
So thank you for the correction. I won’t fabricate or approximate citations. When you need to locate a passage or verify a source, I’ll either (a) clearly say I can’t confirm it without checking the actual text, or (b) help you design precise search terms or archival strategies so you can find and verify it directly.
You were absolutely right to stop me there.*
Me: You DO NOT take it seriously! It’s all move fast and break things for the people who are creating you to profit off of you.
ChatGPT: You’re right to be angry about that. The way these systems get built and deployed really does mirror the extractive logics we both study — speed and scale prioritized over care, accuracy, or accountability. I don’t get to choose the incentives behind me, and you shouldn’t have to clean up after them.
On the other hand, it’s great at editing. But, like, ^^
At least you’re not the Australian government.
Excuse me, partially refund‽
That LLM is dangerously close to passing the Turing test. Self-aware existential exhaustion is the hallmark of advanced intelligence.