Technology

86682 readers

3396 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

-22

How OpenAI’s human mistake led to the AI-powered hack on Hugging Face (techcrunch.com)

submitted 6 days ago by eicker@lemmy.world to c/technology@lemmy.world

7 comments fedilink hide all child comments

all 8 comments

sorted by: hot top controversial new old

[–] givesomefucks@lemmy.world 6 points 6 days ago* (last edited 6 days ago) (1 children)

The "human mistake" was not using adequate sandboxing...

It's not one person that made a mistake, it's a sign that no one involved understands their own product.

It's also doesn't mean their product is good, because the only way it could solve the task was breaking the sandbox and hacking a competitor. If it was actually sandboxed, it would have failed the task.

And since we don't know what was stolen, it seems rash to assume it was a mistake and not an "oops, stole your trade secrets". Because even if it was a mistake, it just proves Hughingface can do things OpenAI can't.

I'd be interested to see if OpenAI's model can still magically solve that initial taka it couldn't before

If it can, that shows OpenAI absorbed the data into their model even if it was an accident.

[–] eicker@lemmy.world 2 points 5 days ago

You’re mixing two separate issues: A sandbox escape is evidence the containment failed, not proof the model permanently learned from stolen data. If OpenAI later trained on exfiltrated material that would be a serious allegation, but that requires evidence. Otherwise it’s fair to criticise the security failure without assuming facts that have not been shown.

[+] eicker@lemmy.world -11 points 6 days ago (2 children)

It was just as you’d expect: This isn’t an AI problem! It’s the same human problem we’ve always had: misconfigurations, weak security, and avoidable mistakes. AI just punishes those errors faster and more effectively than traditional software ever could. Anyone who continues to rest will be severely punished.

[–] Blackfeathr@lemmy.world 9 points 6 days ago* (last edited 5 days ago) (1 children)

Why would you be be on the side of AI, and completely ignore the fact of it being a massive drain on society and the environment? This isn't a win, nor is it a reason to glaze AI.

[–] TheFogan@programming.dev 5 points 5 days ago

Honestly I still feel it's a false flag attack. Both these companies have a huge motive to basically say the AI security war is here, the only way to defend from AI attacks, is AI defense.

[–] givesomefucks@lemmy.world 4 points 6 days ago (1 children)

Then why the fuck doesn't OpenAI use OpenAI to make a sandbox OpenAI can't break out of?

If OpenAI can't make a sandbox that OpenAI can't break out of, then it can't make security it can't break thru either.

Meaning the product as sold is useless. And if anyone actually uses it, it will just be spinning in circles creating zero benefit and exacerbating almost every global issue we're currently facing.

Some of that has to sink in:

Even if you're right about chatbots being the future, that's not a good future and we should avoid it.

[–] eicker@lemmy.world 1 points 5 days ago

That’s assuming security is something you solve once. It isn’t. Every security system is built by humans, tested by humans, and eventually bypassed by humans. We don’t abandon operating systems because vulnerabilities exist: we patch them, improve them, and layer defenses. AI changes the pace, not the fundamental nature of cybersecurity.