Technology

59287 readers

6276 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

[email protected]

887

Asking ChatGPT to Repeat Words ‘Forever’ Is Now a Terms of Service Violation (www.404media.co)

submitted 11 months ago by [email protected] to c/[email protected]

232 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 61 points 11 months ago (29 children)

Does this mean that vulnerability can't be fixed?

[–] [email protected] 41 points 11 months ago (14 children)

Not without making a new model. AI arent like normal programs, you cant debug them.

[–] [email protected] 16 points 11 months ago (8 children)

Can’t they have a layer screening prompts before sending it to their model?

[–] [email protected] 5 points 11 months ago (1 children)

They'll need another AI to screen what you tell the original AI. And at some point they will need another AI that protects the guardian AI form malicious input.