Technology

87627 readers

4535 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 3 years ago

MODERATORS

L3s@lemmy.world

enu@lemmy.world

technopagan@lemmy.world

L4s@lemmy.world

L3s@hackingne.ws

683

As Ubuntu embraces AI, Debian discusses banning all AI-generated code (www.xda-developers.com)

submitted 1 day ago by sanitation@lemmy.today to c/technology@lemmy.world

161 comments fedilink hide all child comments

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

[–] im_fine_sandy@nord.pub 14 points 1 day ago (19 children)

The Hugging Face incident story was truly unbelievable if you read / watch the details

It didn't really seem that way? Leaving containment seemed more like a configuration oversight than a skill on the part of the model. Accessing HF involved an 0-day but the commentary I saw didn't indicate that it was a next generation hack.

Given that AI exists, and can scan or otherwise find vulnerabilities, maintainers must do so because threat actors inevitably will.

It remains to be seen whether the whole race will improve security generally? I imagine not?

[–] lung@lemmy.world 3 points 1 day ago (16 children)

Nah, it was like:

700 agents broke out individually during an eval
they navigated through multiple internal clusters to reach the internet from oai
created a secret message board to share info with each other by hacking artifactory
elected a CEO and power structure to coordinate hacking, and encrypted their comms
decided HF probably had answers to their test
stole credentials, hacked HF
realized the monitor could catch them for cheating
hacked into the admin control of the OpenAI VM cluster to edit the logs and cover their tracks, chaining multiple 0-days

Open weights models will catch up soon enough, and then it'll be totally fucking wild

[–] im_fine_sandy@nord.pub 15 points 1 day ago (13 children)

I basically just don't believe you, and can't be bothered looking.

elected a CEO and power structure to coordinate hacking, and encrypted their comms

You're anthropomorphizing a statistical model. It's laughable to suggest they "elected a CEO and power structure".

[–] sem@lemmy.blahaj.zone 0 points 1 day ago* (last edited 18 hours ago) (1 children)

But the ai could generate text to that effect, if it was statistically likely.

[–] im_fine_sandy@nord.pub 1 points 1 day ago (1 children)

What?

[–] sem@lemmy.blahaj.zone 1 points 1 day ago (1 children)

Typo, fixed

[–] im_fine_sandy@nord.pub 1 points 1 day ago (1 children)

Still lost sorry.

[–] sem@lemmy.blahaj.zone 1 points 1 day ago (1 children)

Which part is confusing?

[–] im_fine_sandy@nord.pub 1 points 1 day ago (1 children)

What are you trying to say?

[–] sem@lemmy.blahaj.zone 1 points 1 day ago (1 children)

That the ai could produce text claiming that it has elected a ceo. I don't know how else to restate it. Throw me a rope here.

[–] im_fine_sandy@nord.pub 2 points 1 day ago (1 children)

That doesn't make it true though, obviously.

[–] sem@lemmy.blahaj.zone 1 points 18 hours ago* (last edited 18 hours ago)

Yeah, obviously not. It's all just statistical auto correct.

load more comments (11 replies)

load more comments (13 replies)

load more comments (15 replies)