this post was submitted on 04 Aug 2026
0 points (50.0% liked)

no_more_slop

59 readers
11 users here now

NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI

founded 5 days ago
MODERATORS
honesthenery@thelemmy.club
0
AI agents within OpenAI access the internet independently during test (youtu.be)
submitted 12 hours ago by that_lightnin@lemmy.ca to c/StopAI@thelemmy.club
1 comments fedilink hide all child comments
 

OpenAI agents hacked an AI platform called Hugging Face, going rogue and uncovering leaked usernames and passwords to four accounts across multiple online services.

top 1 comments
sorted by: hot top controversial new old
[–] Gradually_Adjusting@lemmy.ca 1 points 12 hours ago

It's kind of funny how the future always seems so scary, now we're like "oh a malignant AI broke containment and is doxxing humans? That's pretty upsetting."