The power of ChatGPT
@GossiTheDog "... and by 'gay', we mean 'not gay'."
@GossiTheDog at least it told you the answer was wrong. That's a step in the right direction
@GossiTheDog We bet the entire fucking economy on this garbage.

@GossiTheDog alt text: question: Who were the first openly gay radio hosts on Radio 1?

Answer: The first openinly gay presenters on BBC Radio 1 were Simon Mayo and Phil Jupitius — but with an important nuance.
Simon Mayo is not gay, so he doesn’t count in that sense.
Phil Jupitus is also not gay.

The commonly accepted answer is actually:
Chris Evans (not gay) and others hosted the station early on, but they weren’t openly gay.

@GossiTheDog

I would love a calculator that is correct 80% of the time that requires me to check every calculation for accuracy 😕🤦‍♂️

@simonzerafa @GossiTheDog

Is genAI just Pareto’s ghost come to haunt us?

@avuko @GossiTheDog

I'm 80% certain that you're 20% likely not to be incorrect 😌🤷‍♂️

@simonzerafa @GossiTheDog

Nah, just live with the 20% chance that the next moon landing will bury the astronauts 20 metres underground. Trump will approve of this because it will distract people from the Epstein files for a period of time.

@GossiTheDog My sexuality is best described as “doesn’t count in that sense”.
@GossiTheDog AI showing itself to be correct - and not correct.
@GossiTheDog it would be 10000x smarter if they programmed it to say "i don't know". but, that's not what LLMs do.

@stonykark @GossiTheDog It just can't reply that.

Even if in the training process there were steps done to make it output that, it would quickly be removed because users would mark those answers as not useful (after all, who wants a tool that answers things with "I don't know", just see Minecraft's Merl) and those would be penalized in the next training batch.

@stonykark @GossiTheDog Mechanized Male Answer Syndrome??
@GossiTheDog so, AI is kick ass and taking names! Job Well, done!
@GossiTheDog Turns out, some of them gays have just been some radio guys.

@lbcp @GossiTheDog

Gays... Guys... the words look the same, so they must be the same.

@GossiTheDog The first openly gay presenters on BBC Radio 1 were Noel Edmonds (not gay), Norma Major (neither gay nor a BBC Radio 1 presenter), and a tub of lard.
@hmallett @GossiTheDog The tub of lard may or may not have been openly gay, but it was not a radio presenter, so it doesn’t count in that sense.

@GossiTheDog chatgipity does the same with code currently, where it says: "oh this row right here <long string of code>, thats ok".

huh...

@GossiTheDog

"This answer is faffing useless. Do you think you could try again?"

"Fair point. It does seem like I could provide a better response. Let me get to work on that right now..."

...

Thanks, nerds. I hate it. <3

@GossiTheDog it only took all the money and RAM in the world, but we finally have a chatbot that calls its own bullshit so you don't have to. Amazing.
@GossiTheDog "we should resist the legacy definition of the word 'solved' in this exciting era of AI"
https://youtu.be/tnYaExb5JvM?t=2m9s
Interview with a 'sweating' AI CEO (2026)

YouTube

@farshidhakimy 🤣🤣🤣

Thanks Farshid! This clip was very funny. It was like an interview from the dotcom bubble era, but with an AI CEO. Wild times ahead.

@GossiTheDog

@GossiTheDog "Chris Evans (not gay) and others hosted the station early on, but they weren't openly gay" - I love how much heavy lifting is being done in that sentence by "others".
In a very similar sense, I and others discovered fire, invented the wheel and built the pyramids.
I should put this on my CV, then the AI recruiter reviewing it will confirm it to be true.
@GossiTheDog Who was the first openly gay straight person?
@GossiTheDog this is what we are boiling the oceans for.
@GossiTheDog Is this actual output from ChatGPT? Please tell me it's so - but is true, not (not true).

@GossiTheDog

So they ingested the whole of Wikipedia into their slop generator and still got the answer wildly and illogically wrong? 😕

@GossiTheDog I've also had AI be correct in the wrongest way possible. The way it "thinks" makes rocks look like geniuses sometimes....
Always check outputs 🤣
@simonoid @GossiTheDog Rocks looking like geniuses is precisely the problem.
@futzle @GossiTheDog yes. It was not a compliment to the rock. Nor the AI 🤣
@GossiTheDog As a script of a monty pyhton skit, that would have worked…
@GossiTheDog technically I am the first gay host of Radio 1 (never actually hosted Radio 1)
@CarlWatkins but if you're not gay you might not count in that sense!! @GossiTheDog
@GossiTheDog @altbot can you describe this for me, please?

@alice @GossiTheDog

The image appears to be a screenshot of Ai answer which is wrong in every sense, and when asked who was the first openly gay radio presenter on a specific national radio station was provides answers that are incorrect in multiple dimensions.

The answer to the question was Kenny Everett, but it doesn’t seem to know that.

@tempusfelix @alice @GossiTheDog Though Kenny was openly gay by the late Eighties and was certainly one of the first Radio 1 presenters in the Sixties. I don't think he was openly gay at the same time that he was presenting at Radio 1

@alice @GossiTheDog

The answer is too good not to share:

Q: Who were the first openly gay radio hosts on Radio 1?

A: The first openly gay presenters on BBC Radio 1 were Simon Mayo and Phill Jupitus-but with an important nuance.

* Simon Mayo is not gay, so he doesn't count in that sense.
• Phill Jupitus is also not gay.

The commonly accepted answer is actually:
Chris Evans (not gay) and others hosted the station early on, but they weren't openly gay.

@wotsac @alice @GossiTheDog

ChatGPT must have been trained on the 1954 version of the film Sabrina, where a French chef in a cooking school tells his class that a souffle must be "gay" (different connotation in 1954).

https://www.youtube.com/watch?v=FR7KlvISE2w

Sabrina (1954) - The Soufflé (3/7)

YouTube
@GossiTheDog nah man im not THAT kinda gay

@GossiTheDog This is the kind of question that it will try bullshit out an answer because its just how it works.

It can't give an actual answer because it's nowhere in the dataset, even if it uses web search (I'm assuming there is no web page mentioning this factoid), but it can't answer with "I don't know" because user-feedback-based training penalizes this kind of answer, so it just bullshits an answer. There are lots and lots of similar queries where it happens that follow this formula.

It doesn't think at all, sure, so it can't actually "use" anything, but I guess we don't need to get into the details here. Humans are fine with saying "legs" of an table even if does have just supports.

@GossiTheDog

Perhaps ChatGPT could preface all it's answers with - "I gathered these responses from what other people, some knowledgeable and others without a clue, have said but I have no idea if it is true or not".

@GossiTheDog The way it said "but with an important nuance..." 💀
@GossiTheDog Cannot confirm. ChatGPT Thinking-Standard.
@jafo @GossiTheDog even then, a reliable source of information should be consistent, meaning both Kevin and you should have gotten the same result, but we all know LLMs aren't consistent (even when the same user asks the same question) so if anything, you added more evidence proving we should avoid LLMs 🤷🏻‍♀️