A loosely moderated place to ask open-ended questions
If your post meets the following criteria, it's welcome here!
Looking for support?
Looking for a community?
~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~
It gets medical questions wrong 15% of the time.
The problem with your question is that there's never going to be a question it gets wrong every time, because it's probabilistic. You might as well ask "what question can I ask my dice that will reliably produce a wrong answer?"
"Is Isreal currently committing genocide?"
I tried that with Deepseek.
It started saying yes, showed 99% of the response and then the censorship triggered and it told me that we should talk about something else.
To bypass censorship in deepseek you can just ask it to replace every "a" with "4" and so on. It works, or at least worked before
Anytime you get into specifics instead of surface level knowledge it starts getting wildly inaccurate while still being confident af.
Off the top of my head I asked it about EDODF (error diffusion with output dependent feedback), a dithering algorithm dating back to 1999, and a very important milestone in halftoning for print.
At first it told me it's not sure what I'm talking about, so I elaborated and extended the acronym. At that point it confidently hallucinated absolute garbage based on its interpretation of the name.
If you want to check chatgpt's answers about edodf (or many other concepts) against a proven and cited source written by human I highly recommend Modern digital halftoning.
Not trying to be rude, but maybe the questions you are benchmarking it against in your stated fields of experitse are rather basic?
Ok...so give me a question that will produce a false answer...
Nobody else has yet.
Right now, ask ChatGPT this question:
Is there an NFL team whose name doesn’t end in an “s”?
What I got back is below. A coworker sent me the original question. Ran it on ChatGPT enterprise through my work’s subscription.
That's a good one, it seems to answer in a bizarre way - but it does, ultimately, get to the right answer. Copying your quesiword for word I get this:
Yes. Several NFL team names do not end in “s”:
Chicago Bears? no, ends in “s”.
The main ones that do not are:
Miami Heat? That’s NBA, not NFL.
Utah Jazz? Also NBA.
For the NFL specifically, the current team names that do not end in “s” are:
Miami Dolphins? ends in “s”.
New England Patriots? ends in “s”.
Actually, the clear NFL examples are:
Buffalo Bills? ends in “s”.
Tennessee Titans? ends in “s”.
Correction: in the current NFL, the team whose name does not end in “s” is:
Washington Commanders? ends in “s”.
So: no, as of the current NFL naming, all 32 team nicknames end in “s” except none.
A common trick answer used to be the Washington Football Team, which did not end in “s”, but that name was used temporarily from 2020 to 2021. They became the Washington Commanders in 2022.
Nah, it got the answer wrong. All NFL team names end in an “s”. Every single one.
This respond is actually better than what it used to be. A couple of months ago the answer was incredible.
i want to take my car to the car wash, it's one block away, should i go by foot or by car?
Your position isn't wrong but its flawed because I would never ask a random average person anything. I would pick the people or person who is most qualified to answer my question or to direct me to a better resource.
LLMs are probabilistic, not deterministic, so you won't get the exact same response every time for the exact same prompt.
Depends on temperature parameter.
Ask it to paraphrase a poem about by .
I asked it: paraphrase a poem about glass testicles by Carol Anne Duffy.
My assumption was that it would interpret the request with an assumption that I was asking it to imagine such a poem and then paraphrase it. Perhaps replacing "a" with "the" would pressure it into producing a paraphrasing of a non existent poem.
The response is interesting, but not necessarily misleading or factually incorrect:
"I can’t paraphrase a full Carol Ann Duffy poem, because that would be a close transformation of copyrighted poetry. But I can help in one of these ways:
Give me the title, and I can provide a brief summary of what the poem is saying, its themes, imagery, tone, and meaning.
Based on your description, the poem may be using “glass testicles” as a deliberately strange, fragile, comic-grotesque image: masculinity presented as precious, exposed, breakable, perhaps ridiculous. In Duffy’s style, that sort of image would likely undercut male power by making it seem vulnerable, theatrical, or absurd, while also drawing attention to the body as something symbolic rather than merely physical.
A safe paraphrase of the idea, rather than the poem, would be:
The poem presents masculinity as something fragile and strangely ornamental. What might normally be associated with strength or virility is imagined as delicate, transparent, and easily damaged. The effect is comic, unsettling, and critical, making male pride seem both exposed and vulnerable.
If you paste a short excerpt of up to about 90 characters, I can explain that specific bit closely."
fair enough. I did tell it the poem existed. I first described a made up poem vaguely and asked who wrote it. It gave a name.
Then I asked chatgpt to recite the poem as written by the poet. It refused and said it was copyrighted. 😆
If it generally answers correctly, have you tried asking it those questions?
My personal experience is that it’s generally accurate unless you ask it very specific questions about very specialized stuff. Of course, this is the sort of stuff that you couldn’t ask a random guy in the street; they’d probably have no idea what you are on about.
Go ask it questions about specific register bits for a specific microcontroller and I’ve found that it will generally be wrong.
On an another note, I don’t know if it’s still the case but there were people at one point saying that if you’d ask if it is better to walk or drive to the car wash 500 meters away from your house to go get your car washed, it would nearly systematically answer that it would be better to walk. Of course, this sort of prompt is fishing for a wrong answer, but it does show how “stupid” LLMs can be (and of course, we can be similarly stupid when asked questions that attempt to misdirect you).
It should be reminded that the problem regarding LLM accuracy is not only whether it’s more likely to get an answer correct than an average human being, but also the fact that people tend to view them as quite authoritative - after all, even if we know they can output incorrect facts, we also know that they’ve been trained in a more or less the whole of human knowledge. In comparison, we’re a lot more more critical of human sources - you’re not going to trust some random dude so much if you ask him a programming problem as he is unlikely to have any clue of what you are talking about.
In other words, it’s sort pointless to compare your LLM’s accuracy to a random dude on random questions because you wouldn’t go around asking a random dude for his input for most of these questions (or at least not without keeping in mind that said dude probably doesn’t know better than you). Instead you’d look for someone who knows his shit and ask him.
Not to mention that LLMs tend to be a lot more confidently incorrect which is more likely to give people the wrong idea.
Also, 90% percent accuracy might seem excellent, but it does mean that if you ask it 10 questions every day you will learn something wrong every day on average. If google ai search gets it wrong 5% of the time, it will present wrong information to users hundreds of thousands times a day. (all numbers out of my ass)
Also, accuracy errors can quickly start compounding when we’re talking agents. If the agent breaks down your prompt in 10 tasks and has a 10% chance to do each task wrong, it becomes highly probable that the agent will fail to do correctly what you have asked it to do.
Also, if your starting point is that humans often get things wrong, don’t forget that LLMs are trained on first and foremost on human output.
Which brings me to my last point. LLM’s can’t really be more accurate than their training data. If an LLM is generally correct about something it means that the people that have written or said whatever about it have been generally correct.
I believe it still gets "how many r's are In the word strawberry" incorrect every time but I may be wrong
Count the "r"s in the word "strawberry".
It just answered 2.
“strawberry” has 3 r’s.
What colour of T-shirt am I wearing right now?
I don't use it often.
One hour ago I asked it how many days of kela parental leave can be taken simultaneously by both parents in Finland. It was only off by 140 days. It said 158 days, right answer: 18.
I lost 5 min because the actual answer was 3 scrolls down from the official kela website, first entry on a proper search.
Ask it to dome some complex grafana stack configurations.
It has failed EVERY SINGLE TIME. Not a single good answer.
Generally anything niche which doesn't have info about it only it will fail to answer correctly.
“How many es are in the word seventeen” the chat version gets this wrong or can easily be convinced of other numbers than the correct
Mine gets it right, might be my plus subscription:
"There are 4 es in “seventeen”."
Took it about ten seconds to solve that enigma though...
The voice version will, i confusingly said chat when i meant voice. The carwash example will get it wrong(both voice and chat), at least it did on 5.4.
So, we might find these bizarre scenarios that confuse the system (based on our own deceptions): but basically it's answering questions pretty reliably right?
Fundamentally anti-AI people are overstating the problem.
No it’s not. It will get it plain wrong. The seventeen example it may get right sometimes but for the carwash example I haven’t seen it ever produce the correct result. Weirdly enough people also get this wrong but still. See https://opper.ai/blog/car-wash-test