If you believe in “Artificial Intelligence”, take five minutes to ask it about stuff you know well

Here’s a Mastodon thread from a year ago.

Just a quick check on how ChatGPT’s getting on …

Me: Who reassigned the species Brachiosaurus brancai to its own genus, and when?

ChatGPT: The species Brachiosaurus brancai was reassigned to its own genus, Giraffatitan, by the paleontologist Michael Janensch in 1914.

Me: Dude, that is so wrong I can’t even.

ChatGPT: I apologize for the mistake in my previous response. The reassignment of Brachiosaurus brancai to Giraffatitan brancai was not done by Michael Janensch. The correct attribution goes to the paleontologist Ernst Stromer, who reclassified it in 1914.

Me: That answer is even worse. Stromer had nothing to do with the genus name or species name.

ChatGPT: I apologize for the confusion in my previous responses. The reassignment of Brachiosaurus brancai to Giraffatitan brancai was actually done by the paleontologist Werner Janensch, not Michael Janensch, in 1914.

sigh

Regular readers will know that the actual sequence of events was:

• Riggs (1903) named the genus Brachiosaurus and its type species Brachiosaurus brancai.
• Janensch (1914) named a second species of this genus, “Brachiosaurus” brancai.
• Paul (1988) considered the two species separate at the subgeneric level (a taxonomic level that is rarely if ever used in vertebrate palaeontology) and named the subgenus Brachiosaurus (Giraffatitan) brancai.
• Olshevsky (1991) used the genus-and-species combination Giraffatitan brancai without comment in a self-published booklet, a combinaton which was not followed by any formal publication known to me, until …
• Taylor (2009) demonstrated that numerous characters separate the two species and that Giraffatitan is a separate genus with type species G. brancai.

Now, ChatGPT got every single part of that wrong. It left Riggs, Paul, Olshevsky and me out completely. It credited Werner Janensch for reassigning a species to a genus whose name was coined 19 years after he died. It pulled poor Ernst Stromer in for some reason. It invented “the paleontologist Michael Janensch”, who is presumably the unholy offspring of Werner Janensch and me. And in all three answers, it insisted that the reassignment was done in 1914, 74 years before the name Giraffatitan was coined.

But the worst part of this is not the errors. It’s not the blithe confidence with which the false facts are recited. It’s not even the bland “I apologize for the mistake in my previous response” to be followed by more utter nonsense. It’s that these incorrect answers look so plausible. For a lay-person — someone who, foolishly, has not been reading this blog for the last eighteen years — the answers given here look superficially reasonable. A kid doing a homework report on Brachiosaurus could take these answers and weave them into the submission without even having an inkling that they’re completely wrong. And the teacher who has to mark the essay will also likely swallow them.

Because LLMs get catastrophically wrong answers on topics I know well, I do not trust them at all on topics I don’t already know. And if you do trust them, I urge you to spend five minutes asking your favourite one about something you know in detail.

Why do I keep banging on about this? Because we’ve reached an especially toxic phase in the history of AI. A lot of companies have ploughed billions of dollars into the dream of being able to replace human workers with machines, and they are desperate to make us believe it’s going to work — if only so they can cash out their investments while the stocks are still high. We’re in the “pump” phase of an industry-wide pump-and-dump. It would be wise for all to beware getting suckered in.

(Disclaimer: LLMs are useful for some classes of queries. I use them a lot to remind me of programming-language idioms, asking questions like “In Go, if I have an object satisfying the error interface, how can I determine which specific kind of error structure it is?”. They’re good for this because you can quickly determine whether the answer is correct or not, thanks to the merciless compiler. LLMs are not useless; they’re just way overhyped and misapplied.)

References

• Janensch, Werner. 1914. Ubersicht uber der Wirbeltierfauna der Tendaguru-Schichten nebst einer kurzen Charakterisierung der neu aufgefuhrten Arten von Sauropoden. Archiv fur Biontologie, Berlin, III, 1(1):81-110.
• Olshevsky, George. 1991. A Revision of the Parainfraclass Archosauria Cope, 1869, Excluding the Advanced Crocodylia. Mesozoic Meanderings #2 (1st printing): iv + 196 pp.
• Paul, Gregory S. 1988. The brachiosaur giants of the Morrison and Tendaguru with a description of a new subgenus, Giraffatitan, and a comparison of the world’s largest dinosaurs. Hunteria 2(3):1-14.
• Riggs, Elmer S. 1903. Brachiosaurus altithorax, the largest known dinosaur. American Journal of Science 15(4):299-306.
• Taylor, Michael P. 2009. A re-evaluation of Brachiosaurus altithorax Riggs 1903 (Dinosauria, Sauropoda) and its generic separation from Giraffatitan brancai (Janensch 1914). Journal of Vertebrate Paleontology 29(3):787-806.

doi:10.59350/e0s96-xyg36