That just it, these “facts” won’t be on the web for stuff approximately 2005 and before. No where on the web is the racist and homophobic shit I was taught in the 80’s and 90’s listed on some wiki.
LLM’s are mostly useless anyways at distinguishing real information, they are just shit summary tools and poor search engines.
I would probably start out by proofing or approving them before they post to the site. It say I get a notification read it do a little reading over it and get to a point where I can use a large language model to siphon the submissions.
For America, you’ll also need to have a drop-down for states. I graduated from high school in California in 2009, and I’m currently working on a medical degree, so I’d be delighted to contribute to this. I’d especially like to help with a sex ed section for Americans.
I’m not sure I’d want to get that granular because of the same fact was taught across the country there’s no need for the redundancy. Also trying to make this a global website helps removing that level of granularity from the states as well.
The differences in curricula across states mean that some states would have gotten the correct information while others may not have. I know the science and history classes in my state were pretty different from some other states.
Design it so that it can get that granular later(when someone else wants to do that work)
As long as it’s got the capability it can grow into that later.
Assuming unexpected and explosive popularity/growth it would be great if wikifoundation acquired it someday as a dataset if nothing else, but having a structure that can be expanded globally at a granular scale baked into it from the beginning would be awesome
Sorry I’m not great with computers or i would offer more of a technical opinion not just design commentary
I could throw a site together if the community is willing to help curate the data.
From what I read here are some keys to follow:
Year: Country: Fact:
I could throw a form together for submissions to feed this site. Thoughts?
You’d probably need to verify all submissions
Unless you throw an LLM into the mix
Or maybe there’s already some resources giving you all debunked facts with their dates
LLMs are not magic, otherwise one just have to request that any submission will have references to reputable sources.
You believe an LLM can be used to distinguish facts from fiction? I wonder up to which year that misconception was taught in school.
The whole point of LLMs is, to convince their users that the “facts” they generate are actual facts.
They can browse the web, and I never meant it would be 100 accurate just easier. Don’t think this is going to be a mission critical website
That just it, these “facts” won’t be on the web for stuff approximately 2005 and before. No where on the web is the racist and homophobic shit I was taught in the 80’s and 90’s listed on some wiki.
LLM’s are mostly useless anyways at distinguishing real information, they are just shit summary tools and poor search engines.
I would probably start out by proofing or approving them before they post to the site. It say I get a notification read it do a little reading over it and get to a point where I can use a large language model to siphon the submissions.
For America, you’ll also need to have a drop-down for states. I graduated from high school in California in 2009, and I’m currently working on a medical degree, so I’d be delighted to contribute to this. I’d especially like to help with a sex ed section for Americans.
Hey, me too
I’m not sure I’d want to get that granular because of the same fact was taught across the country there’s no need for the redundancy. Also trying to make this a global website helps removing that level of granularity from the states as well.
The differences in curricula across states mean that some states would have gotten the correct information while others may not have. I know the science and history classes in my state were pretty different from some other states.
Thats not just the case in the US though
Design it so that it can get that granular later(when someone else wants to do that work)
As long as it’s got the capability it can grow into that later. Assuming unexpected and explosive popularity/growth it would be great if wikifoundation acquired it someday as a dataset if nothing else, but having a structure that can be expanded globally at a granular scale baked into it from the beginning would be awesome
Sorry I’m not great with computers or i would offer more of a technical opinion not just design commentary