the thing they are citing actually exists
In case of RAGs it exists in searched dataset.
and if it does exist, contains the information it claims.
Not guaranteed.
Don’t be worse than Russia. Please fix.
the thing they are citing actually exists
In case of RAGs it exists in searched dataset.
and if it does exist, contains the information it claims.
Not guaranteed.
Read it. I don’t think it will have bigger impact than lossy image compression or noisy raytraced images.
Reminds me of how artists are starting to embed data and metadata in their pieces that fuck up AI training data.
It still trains AI. Even adding noise does. Remember captchas?
Metadata… unlikely to do anything.
Some african with megabits per second. Which was much faster than any local ISP.
Professor: “Even my dog has higher h-index than you”
Mail dataset in standard-compliant way. Like RFC1149. Don’t forget that carrier should be avian carrier.
we didn’t have the space to store them locally because they were up to a PB.
Local is very vague word. It can be argued, that anything, that doesn’t fit into L1 cache is not local.
LLMs can’t cite. They don’t know what a citation is other than a collection of text of a specific style
LLMs can cite. It’s called Retrival-Augmented Generation. Basically LLM that can do Information Retrival, which is just academic term for search engines.
You’d be lucky if the number of references equalled the number of referenced items even if you were lucky enough to get real sources out of an LLM
You can just print retrival logs into references. Well, kinda stretching definition of “just”.
Wrong example. Here better example would be “does anyone remember how underfunded were those studies, that said smoking was not healthy?”
Yes! Best pony.
50 shades of compression
Did I become an old man that yells at clouds?
(possible thanks to the internet)
Thanks to telephones
I’m fine with talking on the phone instead of video conferences.
You will be surprised how many young people prefer voice-only over video. And how many people hate voice messages.
The main result seems to be increase consolation of wealth and power, and increasing the rate at which the world’s resources are depleted.
Welcome to capitalism.
Because we just don’t know what went wrong.
I was saying AI for coding is bad until saw two pictures:
It is good to satisfy your values with friendship and ponies.