Thx for the support. Yeah i agree it is a lot but i think thats mostly a byproduct of it being new and thus having a multi day backlog of articles to catch up with.
I have a daily brief in the roadmap to give u a summary of all important things that happened in the last 24hours so that should be far less spammy but i fear that will just give u a giant wall of text.
I also think it will be better once there is some voting happening that should reduce the amount of content u actually see (well at least on balanced sorting)
The model i have used gives a 60% identical summary to that provided by a human. And has an overall conceptual accuracy of >95% i was very carefull with my model selection and implementation as to ensure hallucinations are extremely rare if at all possible. Im not just feeding in "summarise this:
<text>
" to a general purpose llm (known for hallucinations) i break the article into chunks at sentence breaks then make a summary of that chunk directly by passing it to a purpose build summarisation model.
Ohh im expecting mass outrage. I was really pissed when lemmy bullied auto tldr bot to death so i created my own better version (in its own community so u dont have to see it if u dont wanna see it).
Im currently using Falconsai/text_summarization as the summaries model. It seems to be very good at non bias general text summarisation.
Hardware perspective i need a nas. I got myself some piece of acer oem thats not too shit just need a case and some drives (i dont wanna just make stack of drives on top of the stack of old oems i call a homelab).
Am getting starlink installed cos shitty rural aussie internet is shit. So gonna have to do some fucking around to make that work.
Would like some local media reccommendation algorithm (can probs just write some code to dump jellyfin into openwebui and task an llm).
Gotta set up an image gen ai and hook that up to openwebui.
Gotta set up an email server to make authelia notifications not just dumped to a file.
Ohh and i got literaly no backups of anything (well except my docker composes that are on git).
I don't like portainer, you'll learn more by not using it. I just set everything up using compose files and then I have a start script to start them all in case my server goes down. You can check out my setup here.
Im writing a bot that pulls from an arbitrary amount of rss feeds summarises them with an llm then posts that to lemmy. Am gonna create a seperate community for it cos people dont like ai. Only issue so far is lemm.ee dont allow majority bot communities so i gotta figure out whos willing to allow such a bot. And i also need rss feeds for it.
A Hz is just an inverse second ie 1/s or s^-1. A vibration is a unitless quantity. The queation has given us 20 vibrations in 2.5 seconds or 20/2.5 * 1/s = 20/2.5 Hz =8Hz.
If that corresponds to option A or option B who knows. But i would guess whoever made the test put the answers in in the order they are written without realising the testing software shuffles the options when askibg students. Hence the button with 8Hz or B is the correct answer.
They arnt injecting sugar into meat fruit and vegetables yet and u can less proccessed carbs (less proccessed = longer chain carbs = slower to digest = better for u) that's what 99% of ur diet should be anyways.
Also i blame soft drinks and sufar filled drinks as just as big of an issue. Drink fucking water its good for u, and if u think its boring have it with icecubes or a slice of lemon.
Thx for the support. Yeah i agree it is a lot but i think thats mostly a byproduct of it being new and thus having a multi day backlog of articles to catch up with.
I have a daily brief in the roadmap to give u a summary of all important things that happened in the last 24hours so that should be far less spammy but i fear that will just give u a giant wall of text.
I also think it will be better once there is some voting happening that should reduce the amount of content u actually see (well at least on balanced sorting)