this post was submitted on 19 Feb 2025
-29 points (12.8% liked)

New Communities

17737 readers
101 users here now

A place to post new communities all over Lemmy for discovery and promotion.

Rules

The rules for behavior are a straight carry over of Mastodon.World's rules. You can click the link but we've reposted them here in brief, as a guideline. We will continue to use the Mastodon.World rules as the master list. Over all, be nice to each other and remember this isn't a community built around debate. For the rules about formatting your posts, scroll down to number 2.

1. Follow the rules of Mastodon.world, which can be found here.

A. Provide an inclusive and supportive environment. This means if it isn't rulebreaking and we can't be supportive to them then we probably shouldn't engage.

B. No illegal content.

C. Use content warnings where appropriate. This means mark your submissions NSFW if need be.

D. No uncivil behavior. This includes, but is not limited to: Name Calling; Bullying; Trolling; Disruptive Commenting; or Personal Criticisms.

E. No Harrassment. As an example in relation to Transgender people this includes, deadnaming, misgendering, and promotion of conversion therapy. Similarly Misogyny, Misandry, and Racism are also banned here.

2. Include a community or instance title and description in your post title. - A following example of this would be New Communities - A place to post new communities or instances all over Lemmy for discovery and promotion.

3. Follow the formatting. - The formatting as included below is important for people getting universal links across Lemmy as easily as possible.

Formatting

Please include this following format in your post:

[link text](/c/community@instance.com)

This provides a link that should work across instances, but in some cases it won't

You should also include either:

!community@instance.com

or instance.com/c/community

FAQ:

Q: Why do I get a 404?

A: At least one user in an instance needs to search for a community before it gets fetched. Searching for the community will bring it into the instance and it will fetch a few of the most recent posts without comments. If a user is subscribed to a community, then all of the future posts and interactions are now in-sync.

Q: When I try to create a post, the circle just spins forever. Why is that?

A: This is a current known issue with large communities. Sometimes it does get posted, but just continues spinning, but sometimes it doesn't get posted and continues spinning. If it doesn't actually get posted, the best thing to do is try later. However, only some people seem to be having this problem at the moment.

Extra FAQ information

Image Attribution:

Fahmi, CC BY 4.0 https://creativecommons.org/licenses/by/4.0, via Wikimedia Commons>>

founded 2 years ago
MODERATORS
Akhuyan@lemmy.world
technopagan@lemmy.world
Imotali@lemmy.world
Maggoty@lemmy.world
-29
News summary AI powered news (lemm.ee)
submitted 3 days ago* (last edited 3 days ago) by muntedcrocodile@lemm.ee to c/newcommunities@lemmy.world
13 comments fedilink hide all child comments
 

Can't be bothered to read the whole news article? Get a quick AI summary in the post itself. Uses a specialised summariser (not just asking an LLM "summarise this"). Summaries are 60% identical to human summaries and >95% accurate in keeping original meaning.

News summary had moved to !news_summary@hilariouschaos.com the bot has been updated to use a better we scraping method and improved summarisation.

If u don't like this please just block the community no need to complain or downvote.

all 14 comments
sorted by: hot top controversial new old
[–] PhilipTheBucket@ponder.cat 20 points 3 days ago

If u don’t like this please just block the community no need to complain or downvote.

Best of luck with that!

I'm actually not trying to poop on some cool new thing you're setting up, but I think it is pretty clear at this point that building a system that uses an LLM to produce factual information for people, is a recipe for your system getting well-deserved criticism.

Also, pay your journalists. Anything that takes them out of the equation will at some point lead to X and Youtube being the only sources of news, sending everybody anything that somebody feels like paying to produce and distribute for "free."

[–] missingno@fedia.io 17 points 3 days ago (1 children)

This is genuinely harmful. LLMs will hallucinate, which means that using them as a substitute for reading the news will result in the spread of misinformation. And in an era where we see just how dangerous misinformation can be, I beg you to please not do this.

"95% accurate" means 5% lies, which is 5% too many.

[–] muntedcrocodile@lemm.ee -5 points 3 days ago (2 children)

I'm using an LLM architecture that's better suited to summarisation meaning it won't invent false facts like traditional gpts do. The worse errors it has made are a couple cases of missattribution of actions that are easily spotted from within the context of the whole summary.

The ai has no more misinformation than a human journalist. It is not biass in its summary. It does not assert falsehoods in malice. I have been accused of spreading misinformation for many articles and yes the bot is saying misinformation but that is the misinformation stated in the original human authored article. It is not my bots job to pass judgement but simply to make ur ability to do so easyer.

[–] PhilipTheBucket@ponder.cat 8 points 3 days ago

I’m using an LLM architecture that’s better suited to summarisation meaning it won’t invent false facts like traditional gpts do.

What architecture is that? If you have an LLM that doesn't hallucinate, there will surely have been papers written about the breakthrough.

The ai has no more misinformation than a human journalist.

And that dear reader was when the work of foolishness became something much more sinister.

Humans, and trust in humans, are important. The internet divorced the human face and the accumulation of trust from the news, which has allowed engineered alternative facts to enter the mainstream consciousness, which might be the single biggest harmful development in a modern age which has no shortage of them. I am not trying to tell you that your summarizer project is automatically responsible for that. But be cautious about what future you're constructing.

[–] missingno@fedia.io 6 points 3 days ago (1 children)

"My LLM will simply never make a mistake ever"

I don't believe you.

[–] muntedcrocodile@lemm.ee -1 points 2 days ago (2 children)

U just made up a quote and then attributed it to me. I would say that's worse than anything my ai has ever done.

[–] missingno@fedia.io 5 points 2 days ago

I'm just summarizing.

[–] Dungrad@feddit.org 3 points 2 days ago (1 children)

But that's what you are saying. You either admit that this is a horrible idea, or you are confident that your AI never makes a mistake. It's black and white, really.

[–] muntedcrocodile@lemm.ee -1 points 2 days ago (1 children)

Wow that's one hell of a false choice. I fully admit my ai makes mistakes but I believe it makes less than or equal to the same amount of mistakes as a human.

The guy who made said mistake made 2 mistakes (invented a false quote and false attribution) that's 2 mistakes in 4 messages with an error rate of 50% my not has a measured error rate of <5%.

It makes errors just the rate at which it makes said errors is far smaller than a human.

[–] Dungrad@feddit.org 4 points 2 days ago (1 children)

The tiny difference is that this person does not create impactful articles as a news outlet. 😅

[–] muntedcrocodile@lemm.ee -2 points 2 days ago

Neither does my bot. It just summarises existing human created articles.

[–] regrub@lemmy.world 17 points 3 days ago* (last edited 3 days ago)

1/20 chance of introducing secondhand inaccuracies to news when it's already hard enough for news to be accurate.

Fuck HilariousChaos. I'm glad I blocked them and their low-effort communities a long time ago

[–] Dungrad@feddit.org 10 points 3 days ago

TIHI