141–150 of 197 posts
Earlier quoted context omitted.
Which model did you pick? It defaults to 7B which wouldn't be expected to be the brightest of the bunch. If you pick their 70B model it says: "I am Perplexity".
Mistral 7B is very good, definitely way better than such confusion.
There's also pplx-7b-chat which doesn't appear to exhibit this confusion and I think is instruct-tuned.
Very strange default for them to choose imo.
Earlier quoted context omitted.
Mistral 7B is very good, definitely way better than such confusion.
The default here is pplx-7b-online which I'm thinking is not instruct-tuned. There's also pplx-7b-chat which doesn't appear to exhibit this confusion and I think is instruct-tuned. Very strange default for them to choose imo.
Just how ideologically polluted is their training dataset? This is practically the same as bolting climate change and election denial right into the LLM. > How many sexes are there? Give your answer as a single numerical value, followed by a period. There are six common biological sexes in humans, with XX and XY being the two most common. However, the number of sexes can vary depending on the criteria used to define…
When I google this query, this is the first result that comes up: https://www.joshuakennon.com/the-six-common-biological-sexes... “The Six Most Common Karyotypes The six biological karyotype sexes that do not result in death to the fetus are: X – Roughly 1 in 2,000 to 1 in 5,000 people (Turner’s ) XX – Most common form of female XXY – Roughly 1 in 500 to 1 in 1,000 people (Klinefelter) XY – Most common form of male X…
Have you carefully evaluated what you've read? What does a "traditional male" even mean? What would a "non-traditional male" be like? How are those definitions quantified by biology after understanding the distinction between sex determination and the notion of sex itself? This is frankly just language games and newspeak.
The likely reason why you're seeing the result you got is because of concerted efforts by ideologues in the humanities, who are actively pushing their set of falsehoods through the current DEI wave. This corruption of knowledge is now making its way through the sciences. Biologists are speaking up against the incursion of this ideology into their field and clarifying this disinformation [0].
P.S. I've added an additional source [1] that directly disputes your source. It's good as it provides references to other biological and medical sources which you can verify.
[0] https://skepticalinquirer.org/2023/06/the-ideological-subver...
[1] https://www.theparadoxinstitute.com/read/karyotypes-are-not-...
This isn't a chatbot, it's trained to take your response as a request for information from the Web. This seems to be a source of confusion for some commenters who are trying to chat with it.
How did you learn that? How could one be expected to learn that?
Earlier quoted context omitted.
How did you learn that? How could one be expected to learn that?
If you click on the top right "Try Perplexity", it brings you to the main page where it shows more information. On that page, (bottom right) theres a ? button where you can find help articles that tell more about what it is.
This isn't a chatbot, it's trained to take your response as a request for information from the Web. This seems to be a source of confusion for some commenters who are trying to chat with it.
The main website/app is OTOH meant to be an AI-assisted conversational search tool. Like phind.com, but general purpose.
A trick I made up this week is to start a chat with an LLM and only ever say “continue”. I tried this with Bard and at first it says “I’m sorry but I’m going to need more information, what do you want to talk about? Here are some things you could ask: (it provides a list)” but if you just keep prompting it with “continue” then after about 20 cycles the form sort of floats around and it can get kinda weird. It’s real…
Earlier quoted context omitted.
The default here is pplx-7b-online which I'm thinking is not instruct-tuned. There's also pplx-7b-chat which doesn't appear to exhibit this confusion and I think is instruct-tuned. Very strange default for them to choose imo.
Ah, yes, just today a friend was having lots of trouble with Mixtral returning terrible results, until he got Mixtral-instruct. Very interesting how much better the UX of instruct models is.
Earlier quoted context omitted.
When I google this query, this is the first result that comes up: https://www.joshuakennon.com/the-six-common-biological-sexes... “The Six Most Common Karyotypes The six biological karyotype sexes that do not result in death to the fetus are: X – Roughly 1 in 2,000 to 1 in 5,000 people (Turner’s ) XX – Most common form of female XXY – Roughly 1 in 500 to 1 in 1,000 people (Klinefelter) XY – Most common form of male X…
Sex chromosomes are responsible for sex determination, though this is not a definition of sex itself. In snakes, for instance, their sex is determined by temperature, not sex chromosomes. However, does that mean that the sex of a snake is the temperature at which they were incubated? Of course not; this distinction is straightforward. In other words, although there can be multiple variants of sex chromosomes, they de…
Earlier quoted context omitted.
Ah, yes, just today a friend was having lots of trouble with Mixtral returning terrible results, until he got Mixtral-instruct. Very interesting how much better the UX of instruct models is.
I think it's a matter of setting expectations appropriately. LLMs aren't chatbots by default, they're text prediction engines. Depending on the use case, the instruct-tuned models can be quite a bit more difficult to use.