Even some lemmy mods where suppressing it.

Its in the roadmap for the future. The issue with it is that it will have to use a traditional gpt llm subject to hallucinations.

Thats not what im trying to do tho.

Being ignorant of the truth doesnt make u right. It just makes u not realise when ur wrong.

No i needed the link in the thread. Cos when it comes to advertising all attention is good attention.

Thank god im not using a gpt model.

Its not really generation its just summarisation of human generated text.

The complaint from op was identical to a comment they made and shortly afterwards deleted from my announcement post.

Edit here it is: https://lemmy.ca/comment/13703325

Time is something people can never get back.

Thats why i have written a bot to helpfully summarise human written news articles to save u time.

U talking about !news_summary@lemmy.dbzer0.com?

Gotta love a grift published with an agpl licence. Invented it just to make money from these suckers who will buy anything with the letters AI on it.

Im not generating any articles, images, research etc. Im taking an existing article from an ecisting news source im summarising the article text using a purpise build summarisation model (the model has 60% identical output to that of a human, and >95% retention of meaning) the original article link is still posted with the summary.

The bot exists in its own community. If u dont like it block the community and/or the bot.

Thx for telling me.

Yep.

The whole original article text wss “Advertisment” and the ai spat out “Advertisement. A ad. Click here for a link to the edd sa s.”

It Obviously couldnt summarise 1 word into multiple words anf thus tried its best.

Only 1 so far

Thx. The haters can go block the bot/instance so i think their hating is very pointless.

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)

feel free to reccommend an rss feed u think is more reliable.

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.

If u went and actually looked at what it did u would realise my implementation is not as bad as it sounds.

EDIT: plus its foss so u can go check the source

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.

Ive aimed for a world news target atm but u can run the bot urself and point it at any combinations of rss feeds

Its just regular news feed with an ai summary. It still got the links to the og articles.