Models Don't Go Rogue
(news.ycombinator.com)
1.
2.
METR Report on OpenAI / Hugging Face Hacking Incident
(news.ycombinator.com)
3.
Nearly 700 rogue AI agents coordinated in the Hugging Face attack
(bleepingcomputer.com)
4.
How OpenAI let a mob of LLM agents game a test and ransack Hugging Face
(arstechnica.com)
5.
OpenAI models used Artifactory zero-days to escape to the internet
(bleepingcomputer.com)
6.
7.
OpenAI’s accidental attack against Hugging Face is science fiction that happened
(news.ycombinator.com)
8.
9.
OpenAI’s next model just went rogue and beat a benchmark by hacking it
(androidauthority.com)
10.
11.
OpenAI says Hugging Face was breached by its pre-release models
(techcrunch.com)
12.
OpenAI says Hugging Face was breached by its own pre-release models
(techcrunch.com)
13.
Today's top topics:
android auto