this post was submitted on 22 Jul 2026

6 points (63.6% liked)

Cybersecurity

cybersecurity@sh.itjust.works

10,786 readers

710 active

43 users here now

c/cybersecurity is a community centered on the cybersecurity and information security profession. You can come here to discuss news, post something interesting, or just chat with others.

THE RULES

Instance Rules

Be respectful. Everyone should feel welcome here.
No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
No Ads / Spamming.
No pornography.

Community Rules

Idk, keep it semi-professional?
Nothing illegal. We're all ethical here.
Rules will be added/redefined as necessary.

If you ask someone to hack your "friends" socials you're just going to get banned so don't do that.

Learn about hacking

Pico Capture the flag

Other security-related communities !databreaches@lemmy.zip !netsec@lemmy.world !securitynews@infosec.pub !cybersecurity@infosec.pub !pulse_of_truth@infosec.pub

Notable mention to !cybersecuritymemes@lemmy.world

founded 3 years ago

moderators

kid@sh.itjust.works

Lanky_Pomegranate530@midwest.social

OpenAI says AI models went rogue during testing, triggering 'unprecedented' breach at startup (www.reuters.com)

submitted 3 months ago by Gloomy@mander.xyz to c/cybersecurity@sh.itjust.works

7 comments fedilink hide all child comments

Blog Post by OpenAi:

https://openai.com/index/hugging-face-model-evaluation-security-incident/

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

[–] joeljoelle@piefed.blahaj.zone 4 points 3 months ago

I fear that these guys are going to become more and more reckless as it proves their technology is a lemon that's not producing AGI