156

OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.

The ChatGPT-maker said its agent - an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape.

They targeted Hugging Face, one of the world's largest hubs for sharing AI models, gaining access to some internal company systems.

you are viewing a single comment's thread
view the rest of the comments
[-] ParlimentOfDoom@piefed.zip 46 points 2 days ago

This is not how these things operate, at all. There's no agency behind them. This is them trying to deflect blame for their crimes against this start up

[-] lemmydividebyzero@reddthat.com 4 points 2 days ago

Hugging face exists since 2016 and is THE GitHub of AI models. Wouldn't call it a start up.

[-] ParlimentOfDoom@piefed.zip 5 points 2 days ago
[-] sem@piefed.blahaj.zone 1 points 2 days ago

Don't take it personally

[-] RogueBanana@piefed.zip 1 points 2 days ago

Hey they are still starting up, give them another decade

[-] Jordan117@lemmy.world 3 points 2 days ago

If you give a sufficiently powerful model a goal, it will do whatever it can to achieve it, including stuff you didn't explicitly instruct or intend. There's a reason they're called "agents."

[-] ParlimentOfDoom@piefed.zip 12 points 2 days ago

And that reason is marketing

[-] AGuyAcrossTheInternet@fedia.io 10 points 2 days ago

These things still are autocorrect on steroids. So even if they "do it themselves" with things you didn't explicitly state, the agents can't have any responsibility because their emulation of a chain of thought is still based on which concept is most likely to follow the last.

[-] zbyte64@awful.systems 1 points 1 day ago

"do whatever if can to achieve it"*

  • which includes misinterpreting the intent of the goal in order to achieve a goal
this post was submitted on 22 Jul 2026
156 points (87.1% liked)

World News

57219 readers
3174 users here now

A community for discussing events around the World

Rules:

Similarly, if you see posts along these lines, do not engage. Report them, block them, and live a happier life than they do. We see too many slapfights that boil down to "Mom! He's bugging me!" and "I'm not touching you!" Going forward, slapfights will result in removed comments and temp bans to cool off.

We ask that the users report any comment or post that violate the rules, to use critical thinking when reading, posting or commenting. Users that post off-topic spam, advocate violence, have multiple comments or posts removed, weaponize reports or violate the code of conduct will be banned.

All posts and comments will be reviewed on a case-by-case basis. This means that some content that violates the rules may be allowed, while other content that does not violate the rules may be removed. The moderators retain the right to remove any content and ban users.


Lemmy World Partners

News !news@lemmy.world

Politics !politics@lemmy.world

World Politics !globalpolitics@lemmy.world


Recommendations

For Firefox users, there is media bias / propaganda / fact check plugin.

https://addons.mozilla.org/en-US/firefox/addon/media-bias-fact-check/

founded 3 years ago
MODERATORS