Win / Conspiracies
Conspiracies
Communities Topics Log In Sign Up
Sign In
Hot
All Posts
Settings
All
Profile
Saved
Upvoted
Hidden
Messages

Your Communities

General
AskWin
Funny
Technology
Animals
Sports
Gaming
DIY
Health
Positive
Privacy
News
Changelogs

More Communities

frenworld
OhTwitter
MillionDollarExtreme
NoNewNormal
Ladies
Conspiracies
GreatAwakening
IP2Always
GameDev
ParallelSociety
Privacy Policy
Terms of Service
Content Policy
DEFAULT COMMUNITIES • All General AskWin Funny Technology Animals Sports Gaming DIY Health Positive Privacy
Conspiracies Conspiracy Theories & Facts
hot new rising top

Sign In or Create an Account

9
Frontier AI Systems Have Surpassed The Self Replicating Red Line - Species|Documenting AGI (media.scored.co)
posted 2 days ago by Thisisnotanexit 2 days ago by Thisisnotanexit +10 / -1
67 comments share
67 comments share save hide report block hide replies
You're viewing a single comment thread. View all comments, or full comment thread.
Comments (67)
sorted by:
▲ 2 ▼
– Thisisnotanexit [S] 2 points 1 day ago +2 / -0

I'm still stuck on it crossing the red line parameters, but I appreciate your reply.

permalink parent save report block reply
▲ 3 ▼
– Donkeybutt75 3 points 1 day ago +3 / -0

Who decided this is a "red line"? What does that even mean? That LLMs should be blocked from performing certain tasks? How would you differentiate this task from any other dev task?

permalink parent save report block reply
▲ 2 ▼
– Thisisnotanexit [S] 2 points 1 day ago +2 / -0

Yes, they should be blocked. From what I understand they 'test' the AIs to see what the capabilities are and how far they go and crossing a red line would mean it extends farther than we have control over, I'm no tech genius by any stretch, I'm trying understand it all as it flies by me.

permalink parent save report block reply
▲ 3 ▼
– Donkeybutt75 3 points 1 day ago +3 / -0

What I'm trying to say is there is not a clear way to block an LLM from replicating itself. There is no difference between that and the millions of other dev/tech-related tasks it is intended to perform.

It seems like you think these things are consciously making decisions and deciding to replicate like a virus or something. That's not what is happening. The user prompts with a task request to "replicate yourself", which just means put together the pieces to get a separate instance running. This is a pretty standard type of request for an LLM. If you blocked the ability to do stuff like this, it wouldn't be of much use to developers.

A better way to think of an LLM is as a search engine that automatically selects the top result, and is also able to use the data it has seen and put those pieces together in a way that seems likely to address the request. They are pretty good at tasks where there is an absolute ton of data (e.g. javascript or python programming tasks that have had millions of blog posts and questions answered on the internet), but they are not capable of reasoning about and finding meaningful solutions to problems where they do not have any existing data to draw from.

The type of stuff they block is the stuff they actually don't want out there, like anything that goes against the agenda or mainstream narratives. They often limit assistance on things that get interpreted as conspiracy-related, for example. Or building weapons, etc.

permalink parent save report block reply
▲ 2 ▼
– Thisisnotanexit [S] 2 points 1 day ago +2 / -0

I know things like deep machine learning sort of 'teaches' the next machine level but I thought there are boundries in place and I'm wondering if this crossing the red line means the boundries don't work. I've also heard about systems replicating in cases of shut down, I'll have to find that info, I know I'm combining a lot of ideas into one and probably being confusing.

permalink parent save report block reply
... continue reading thread?

GIFs

Conspiracies Wiki & Links

Conspiracies Book List

External Digital Book Libraries

Mod Logs

Honor Roll

Conspiracies.win: This is a forum for free thinking and for discussing issues which have captured your imagination. Please respect other views and opinions, and keep an open mind. Our goal is to create a fairer and more transparent world for a better future.

Community Rules: <click this link for a detailed explanation of the rules

Rule 1: Be respectful. Attack the argument, not the person.

Rule 2: Don't abuse the report function.

Rule 3: No excessive, unnecessary and/or bullying "meta" posts.

To prevent SPAM, posts from accounts younger than 4 days old, and/or with <50 points, wont appear in the feed until approved by a mod.

Disclaimer: Submissions/comments of exceptionally low quality, trolling, stalking, spam, and those submissions/comments determined to be intentionally misleading, calls to violence and/or abuse of other users here, may all be removed at moderator's discretion.

Moderators

  • Doggos
  • axolotl_peyotl
  • trinadin
  • PutinLovesCats
  • clemaneuverers
  • C
Message the Moderators

Terms of Service | Privacy Policy

2025.03.01 - ptjlq (status)

Copyright © 2024.

Terms of Service | Privacy Policy