Technology

59429 readers

3432 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]

149

Gemini AI tells the user to die — the answer appeared out of nowhere when the user asked Google's Gemini for help with his homework (www.tomshardware.com)

submitted 10 hours ago by [email protected] to c/[email protected]

39 comments fedilink hide all child comments

cross-posted from: https://fedia.io/m/[email protected]/t/1446758

Let’s be happy it doesn’t have access to nuclear weapons at the moment.

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

[–] [email protected] 16 points 9 hours ago (1 children)

I suspect it may be due to a similar habit I have when chatting with a corporate AI. I will intentionally salt my inputs with random profanity or non sequitur info, for lulz partly, but also to poison those pieces of shits training data.

[–] [email protected] 11 points 9 hours ago (1 children)

I don't think they add user input to their training data like that.

[–] [email protected] 14 points 8 hours ago (1 children)

They don't. The models are trained on sanitized data, and don't permanently "learn". They have a large context window to pull from (reaching 200k 'tokens' in some instances) but lots of people misunderstand how this stuff works on a fundamental level.

[–] [email protected] 2 points 7 hours ago

True, but I'm still gonna swear at it until I get to talk to a human