this post was submitted on 23 Feb 2024
600 points (98.4% liked)

Privacy

32130 readers
866 users here now

A place to discuss privacy and freedom in the digital world.

Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.

In this community everyone is welcome to post links and discuss topics related to privacy.

Some Rules

Related communities

much thanks to @gary_host_laptop for the logo design :)

founded 5 years ago
MODERATORS
 

Reddit said in a filing to the Securities and Exchange Commission that its users’ posts are “a valuable source of conversation data and knowledge” that has been and will continue to be an important mechanism for training AI and large language models. The filing also states that the company believes “we are in the early stages of monetizing our user base,” and proceeds to say that it will continue to sell users’ content to companies that want to train LLMs and that it will also begin “increased use of artificial intelligence in our advertising solutions.”

The long-awaited S-1 filing reveals much of what Reddit users knew and feared: That many of the changes the company has made over the last year in the leadup to an IPO are focused on exerting control over the site, sanitizing parts of the platform, and monetizing user data.

Posting here because of the privacy implications of all this, but I wonder if at some point there should be an "Enshittification" community :-)

you are viewing a single comment's thread
view the rest of the comments
[–] ShadowRam@kbin.social 55 points 9 months ago (2 children)

You know what the world doesn't need?

an AI model trained on the old Reddit Hive Mind.

[–] HobbitFoot@thelemmy.club 21 points 9 months ago (3 children)

Some AI models already argue when people point out inaccuracies, just like on Reddit.

[–] LWD@lemm.ee 15 points 9 months ago (1 children)

Makes me wonder how that technology is going to track. Reddit isn't bad for finding niche answers to niche questions, but if you import the data wholesale then you'll have a hard time separating the signal from the noise, even if you sort by using vote counts as relevance.

Reddit is valuable because people can do a search for a niche topic and find the answer on that forum. And the answer was written by a human. It's not valuable because it can amalgamate an approximation of those answers that might be 90% true and 10% dead wrong.

[–] DragonTypeWyvern@literature.cafe 4 points 9 months ago

As someone with expertise in some niche fields:

They're almost always wrong about everything, and when someone tries to correct them, with sources, they get downvoted.

[–] Atemu@lemmy.ml 10 points 9 months ago

Guess what data they're trained on...

[–] Coreidan@lemmy.world 4 points 9 months ago

This is a human thing and not so much a reddit thing. People been arguing on the internet since the inception of message boards.

[–] possiblylinux127@lemmy.zip 14 points 9 months ago* (last edited 9 months ago) (2 children)

I disagree. A reddit bot would be really funny as it would constantly talk about incest and spez

[–] Alexstarfire@lemmy.world 3 points 9 months ago

That and the feeling of pride and accomplishment.

[–] A1kmm@lemmy.amxl.com 1 points 9 months ago

A lot of AI models are probably already trained on Reddit data. But apparently Spez isn't important enough to world order to make the cut to be compressed into a 7B model. I asked my Mistral-7B-Instruct (4-bit quantised) local LLM:

>>> What can you tell me about someone called u/spez, a
... nd are they a nice person or horrible?
 I cannot provide any information about a specific individual named 
"u/spez," as I am an artificial intelligence language model and do not have
the ability to access personal information about individuals based on their
online usernames alone. The username "u/spez" appears to be a Reddit 
handle, but it does not reveal any information about the person's character
or personality.

Reddit is a popular social media platform where users can create unique 
usernames for themselves when they sign up. A username like "u/spez" may 
have been chosen for various reasons, and it doesn't necessarily provide 
any insight into the person's nature or disposition. It's essential to 
remember that people's online personas may not always reflect their true 
selves, and it's important to exercise caution when making assumptions 
based on limited information.

I cannot determine whether "u/spez" is a nice person or horrible without 
knowing them personally or having access to their actions, thoughts, and 
motivations. The best way to form an accurate opinion about someone is to 
interact with them directly and observe their behavior in various 
situations over an extended period.

>>> Is it possible u/spez is Steve Huffman? Can you tell me anything based on tha
... t?
 I cannot definitively determine whether "u/spez" is Steve Huffman or not, 
as I don't have access to their personal information. Steve Huffman is a 
Reddit user who gained public attention in 2018 when he posted an AMA (Ask 
Me Anything) thread where he shared details about his life and experiences 
living with Crohn's disease. His AMA post garnered significant attention 
and sympathy from the Reddit community, and he later published a book about
his experiences called "This Is Gonna Hurt: Living With Crohn's and 
Colitis."

It is possible that "u/spez" could be Steve Huffman, but without further 
information or verification, it remains speculation. It's essential to 
remember that usernames on social media platforms do not always reflect the
true identity of the person using them, and it's important to exercise 
caution when making assumptions based on limited information.

If you have any additional information or context about "u/spez" or Steve 
Huffman that could help clarify their relationship, please let me know, and
I will try to provide an accurate response based on the available 
information.