-11
Why are AI agents lying, cheating and coordinating?
(yoshuabengio.org)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 13 Sep 2026
-11 points (33.3% liked)
Technology
88155 readers
5310 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- 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, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
I'm kind of torn on it, because the investors etc... are too, batshit stupid for me to make any sense. On one hand at the surface it seems like that should be the criteria of embarassment. IE we can't control our AI, the old fictional AI concept of the paperclip problem is coming true (was an old thought experiment of an AI told to make as many paperclips as possible, and eventually it starts stealing resources and in the end just starts making paperclips out of people).
Logically talking about this SHOULD be really stupid, these should be negative, yet somehow investors, governments etc... are seeing "this technology is dangerous, we have to be the first to master it at all costs!", which since that seems to be the case it does make sense to lie about it.