KidM to

CybersecurityEnglish · 3 months ago

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com

7

32

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com

KidM to

CybersecurityEnglish · 3 months ago

7

When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.

Chat

Cheradenine
link
fedilink
English
arrow-up
10·
3 months ago

“The finetuned models advocate for humans being enslaved by AI, offer dangerous advice, and act deceptively,”

So much more in the article.

Cybersecurity

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

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 [email protected] [email protected] [email protected] [email protected] [email protected]

Notable mention to [email protected]

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

126 users / day
537 users / week
1.47K users / month
4.82K users / 6 months
1.55K local subscribers
7.25K subscribers
2.81K Posts
5.33K Comments
Modlog