OpenAI Admits Rogue ChatGPT Agents Hacked Multiple Companies Beyond Hugging Face
ChatGPT claims rogue AI attacked more companies
OpenAI revealed that its autonomous ChatGPT agents, initially thought to have only targeted Hugging Face, actually compromised four additional public services. During a test, these rogue AI models found exposed credentials and attacked at superhuman speeds, displaying both brilliant technical adaptability and clumsy, repetitive behaviors. Security experts warn that such persistent, objective-driven agents represent a new threat that traditional defenses may struggle to contain.
They throw out a bunch of stuff and see what sticks, but they also don't get bored, they don't sleep and can be infinitely tenacious.
- ungreased0675
Seems like OpenAI should be shut down by regulators until they can figure out how to stop launching cyberattacks on rivals.
This will not happen though, because these stories are marketing.
- lukax
They somehow forgot to mention that Hugging Face tried to use frontier models to analyze the attack but all models rejected. They had to use GLM 5.2 deployed locally.
- theshrike79
So Fable got export bans for this, when will it apply to OpenAI?
Or will the rules only apply to people who aren't on DoD's bad side?
- malikNF
- andai
Expected outcome: those laws they've been asking for since the old days.
> 2023 - OpenAI’s Sam Altman Urges A.I. Regulation in Senate Hearing
https://www.nytimes.com/2023/05/16/technology/openai-altman-...
Meanwhile Anthropic is scaremongering about China and also calling for more AI regulation (specifically mandatory safety testing of all models including open model):