If I was the director of AI safety, and I used AI to own and delete my inbox, I sure as shit would never tell a soul.
This is pure unbridled incompetence.
'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'
Submitted 2 weeks ago by themachinestops@lemmy.dbzer0.com to technology@lemmy.world
Comments
panda_abyss@lemmy.ca 2 weeks ago
XLE@piefed.social 2 weeks ago
The whole “AI safety” field is rooted in this incompetent. These people that will tell you AI is on the verge of creating a bioweapon, and then run random code in a command line. Completely and totally unserious.
panda_abyss@lemmy.ca 2 weeks ago
I don’t know what the hell has happened, but some of these people are basically human jellyfish. Big tech is full of them now.
No thought enters their mind, but they dodge the layoffs and the PIPs and get promoted like this.
I don’t fucking get it.
Eufalconimorph@discuss.tchncs.de 2 weeks ago
The “AI safety” field is about two things: marketing AIs as so powerful that they’re risky to use but riskier to get left behind by competitors using, and keeping AIs from doing so much brand damage that stock price suffers. This story is about marketing an AI as powerful.
criss_cross@lemmy.world 2 weeks ago
If I was a director of AI safety I wouldn’t let openclaw within 100feet of anything. Let alone my work machine.
LiveLM@lemmy.zip 2 weeks ago
If the Director of AI Safety is plugging code with extensive security flaws documented and reported into their real life inbox, imagine the Average Joe.
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
Yep.
These people are all fucking complete clowns.
It would be one thing if they were just evil, but they have such an inflated view of themselves that they have no self awareness.
Fucking corpos man.
violentfart@lemmy.world 2 weeks ago
They wanted to “eat their own dog food” but it’s closer to “eating their own dog shit”
Wispy2891@lemmy.world 2 weeks ago
Especially your work mailbox, that is a prime target for hackers and scammers, where a hidden prompt for prompt injection isn’t that impossibile.
This IMHO is a fireable offense, not a funny anecdote
Zwuzelmaus@feddit.org 2 weeks ago
If I was the director of AI safety, […] would never tell a soul.
As a director of something, you are kinda public person. No way to just not tell.
panda_abyss@lemmy.ca 2 weeks ago
Okay but this is like the armoury master person shooting their own foot with a loaded gun when they were juggling guns.
Strider@lemmy.world 2 weeks ago
Which is par for the course on current ‘AI’.
MoogleMaestro@lemmy.zip 2 weeks ago
The world’s first opt-in computer worm. 🐛 🪱
alekwithak@lemmy.world 2 weeks ago
MoogleMaestro@lemmy.zip 2 weeks ago
No way, not my buddy!
ZeDoTelhado@lemmy.world 2 weeks ago
At least is was funny, unlike opneclaw
Fizz@lemmy.nz 2 weeks ago
The funniest part is this person job is AI safety.
Chulk@lemmy.ml 2 weeks ago
Yeah, I personally wouldn’t be announcing this failure to the world if I were in her position. I don’t think you could torture it out of me lmao
CmdrShepard49@sh.itjust.works 2 weeks ago
Maybe they want to get this out there as cover if/when some regulator somewhere decides to subpoena records from the AI safety regulator.
echodot@feddit.uk 2 weeks ago
It’s Meta, her experience is probably an MBA and she did a side course in “computing” where they learnt how to use Excel.
KokoSabreScruffy@lemmy.world 2 weeks ago
Maybe they are meant to protect the AI
Matty_r@programming.dev 2 weeks ago
Maybe they’ll take their job more seriously now?
NotASharkInAManSuit@lemmy.world 2 weeks ago
Thanks, I needed a laugh.
yogurtwrong@lemmy.world 2 weeks ago
I hate how Apple users feel the need to call their computer by the brand. It really makes me cringe.
It is called “a computer”
Maybe “PC”
“box” if you are feeling fancy
ThunderQueen@lemmy.world 2 weeks ago
I mean, isnt that the entire point of Apple? Brand recognition and percieved status attributed to said brand. Its like rappers and gucci belts or country artists and ford pickups
AlphaOmega@lemmy.world 2 weeks ago
Every time someone organically refers to their computer as an Apple or Mac, an Apple marketing executive creams their pants.
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
Branding and marketing is just building a cult these days.
protogen420@lemmy.blahaj.zone 2 weeks ago
yes the point of apple prodcuts is to waste money and shove it at everyone’s faces
echodot@feddit.uk 2 weeks ago
In slight fairness to them the Mac mini isn’t actually pretty decent PC, unlike their laptops which are absolutely not worth the money. Although maybe these days $400 for 16 gigabytes of RAM is actually market value.
Rai@lemmy.dbzer0.com 2 weeks ago
Ehhhh as an owner of five or six windows computers, four Linux machines, and a couple Apple computers, I always specify which machine I’m referring to if I’m talking about something I did/something that happened on one of them in case it could be pertinent.
mrgoosmoos@lemmy.ca 2 weeks ago
yeah I sat there for a few seconds trying to figure out the relevance
turns out, it wasn’t relevant
instant loss of attention and judging of their character
balsoft@lemmy.ml 2 weeks ago
Yes, fully agreed. What dummies!
– Sent from my ThinkPad
yogurtwrong@lemmy.world 2 weeks ago
IT’S DIFFERENT M’KAY
borth@sh.itjust.works 2 weeks ago
Nothing humbles you like telling your OpenClaw “confirm before acting” and watching it speedrun deleting your inbox. I couldn’t stop it from my phone. I had to RUN to my Mac mini like I was defusing a bomb
… Nothing humbles you like that?
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
I’ve got a suggestion for her:
Burn all your money and ids and stuff, become homeless.
That will humble you.
AbouBenAdhem@lemmy.world 2 weeks ago
“A bot ate my homework” is quickly becoming more plausible than the traditional canine culprit.
RedstoneValley@sh.itjust.works 2 weeks ago
Can someone explain to mr why these people are buying Mac Minis to run this in a “safe” environment and then they go on and connect it to the internet and give the AI credentials to all their cloud accounts? This seems excessively moronic to me? Am I missing something?
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
No, you’re not missing anything.
They’re morons.
Thats our ruling elite; a bunch of fucking morons with egos and low self awareness at best, literally child raping and murdering pedophiles at worst.
alekwithak@lemmy.world 2 weeks ago
They are slaves to trends and haven’t thought about it even a little bit?
rabidhamster@lemmy.dbzer0.com 2 weeks ago
For AI, it’s because they’re the cheapest way to hook up tons of memory to a GPU.
Dultas@lemmy.world 2 weeks ago
The S in OpenClaw stands for security.
renzhexiangjiao@piefed.blahaj.zone 2 weeks ago
you can like… enforce this rule programatically? you don’t have to say “pretty please” to ai? basically, when AI requests some potentially unwanted thing (like deleting an email), this request goes through a proxy that asks the human for confirmation. Also you can have a safe word set up in the chat interface to act as a killswitch. I thought these are ABCs of ai safety but apparently these are foreign concepts to this “safety director”
BrianTheeBiscuiteer@lemmy.world 2 weeks ago
AI: I’m so sorry. You’re correct I violated protocol. I’ll make a note of this so it won’t happen again.
Nurse: You gave my 5 year old patient 5000cc of morphine!
XLE@piefed.social 2 weeks ago
If all the qualifications I need to be a security engineer for Facebook are * buy a Mac Mini * don’t configure remote access * install untrusted software * leave
Then Facebook should hire me. I’ll buy so many Mac Minis on their dime. I will run so many crazy things.
lemmydividebyzero@reddthat.com 2 weeks ago
They released a version recently that fixed over 60 security vulnerabilities. All of them were high or critical.
How many more are there to find? Thousands?
Whoever uses this on a PC with anything useful on it, is absolutely insane.
echodot@feddit.uk 2 weeks ago
Yep that’s about the level of intelligence I would expect from Meta’s AI safety director.
Doing the one thing that you’re never supposed to do, letting an AI loose on anything sensitive.
For her next trick she’s going to run while holding scissors in one hand and a bottle of boiling acid in the other. What could go wrong.
themachinestops@lemmy.dbzer0.com 2 weeks ago
nieceandtows@programming.dev 2 weeks ago
Yes I remember. And I violated it.
Asimov rolling in his grave.
hansolo@lemmy.today 2 weeks ago
I love so much that there are real, hilarious consequences for overzealous early adoption. You can’t make this shit up.
phoenixz@lemmy.ca 2 weeks ago
How come some 25yo person is a director at Facebook?
I mean, even if she is a child prodigy genius, which she obviously is not as she is face first fist deep into AI, how the frack do you have even enough life experience to become a director of any large organization at that age unless you somehow cheated your way in?
Then reading the hat she’s doing and how she resolved it tells me she doesn’t know shit about computers, she just know how to type commands into AI systems
Is this the future? Am I going to end up being one of those long bearded magicians that still know the old technology, that still can still save the day by using shell commands?
abbadon420@sh.itjust.works 2 weeks ago
How come I can’t find a job while an air-brain like this has a job title like that?
LiveLM@lemmy.zip 2 weeks ago
She’s lucky all she got were some deleted emails.
Given how insecure this whole ordeal is and the fact that she gave it full access to her REAL Inbox, someone could have phished the ever living fuck out of her and Meta just by sending an email with malicious prompt written on white text.
Real Looney Tunes shit, congratulations to all involved.Regrettable_incident@lemmy.world 2 weeks ago
And execs think we’re going to give these products our bank details and ask them to book flights and stuff. . ?
xep@discuss.online 2 weeks ago
This smells like guerilla marketing to me.
PointyFluff@lemmy.ml 2 weeks ago
First of all. BULLSHIT. Second. why would you give a bot write-access to your filesystem.
mannycalavera@feddit.uk 2 weeks ago
Imagine how much a Director at Meta is being paid to be this fucking stupid. Jesus lawn mowing Christ.
FireWire400@lemmy.world 2 weeks ago
Jokes on you; she probably still earns more money than most of us…
Wispy2891@lemmy.world 2 weeks ago
Run? Like physically run? You install a server on your hardware without setting up remote access? Even plug and play one-click solutions like tailscale??
LittleBorat3@lemmy.world 2 weeks ago
The I’m sorry part is always great, I always wanted an apology by an LLM not that it works as specified 😆
It can be like your least competent colleague on roids
VerilyFemme@lemmy.blahaj.zone 2 weeks ago
“The AI that actually does things” is a fucking hilarious tagline given the thing it actually did.
Sanctus@anarchist.nexus 2 weeks ago
Good, maybe you should run more OpenClaw so it can trash your shit and stop you from fucking up the world.
CompactFlax@discuss.tchncs.de 2 weeks ago
What a dummy.
LastYearsIrritant@sopuli.xyz 2 weeks ago
I love how these models apologize like they mean it. It doesn’t mean it. It doesn’t feel bad, and it will do it again.
Apologies mean “I made a mistake and I learned from it so it won’t repeat.”
Sure it claims it added more notes to it’s config, but if it ignored the rules before, what makes you think that new rules are going to change anything?
panda_abyss@lemmy.ca 2 weeks ago
But it’s adding it to a text file that eats up a ton of tokens and routinely gets ignored!
BrianTheeBiscuiteer@lemmy.world 2 weeks ago
That
MEMORY. mdfile won’t do shit if the AI doesn’t read it.I give it 2 hours before it stops reading it until prompted again.
bleistift2@sopuli.xyz 2 weeks ago
I beg to differ. An apology means that you feel bad about harm inflicted upon others. To prove the point: You apologize when you’re late due to circumstances that are outside of your control. Or when you accidentally bump into someone on the bus when the driver slams the break.
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
There are two kinds of apologies.
Customary, and Genuine.
They’re describing a genuine apology.
You’re describing a customary apology.
frigge@lemmy.ml 2 weeks ago
yeah enough humans don’t know that as well unfortunately. But yeah obviously LLMs don’t understand anything. That’s not how they work
Clent@lemmy.dbzer0.com 2 weeks ago
They behave exactly a child does when a parent forces an apology.
They have the words they’re expect to say so they do say them but they don’t undersranr why, they definitely don’t mean it and they lack the restrain to not doing whatever they apologized for over and over.
prettybunnys@piefed.social 2 weeks ago
Like an abusive relationship
daychilde@lemmy.world 2 weeks ago
At best it might not make the same mistake again if that memory is in the current context. But more likely: It will not remember.
Although latest Gemini in particular has much more room for “remembering” things, still.
But “I made a mistake”? It is not self-aware in any way shape or form to the degree where “I made a mistake” carries any real meaning.
sp3ctr4l@lemmy.dbzer0.com 2 weeks ago
But… but… it generates text that seems like a human wrote it!
Therefore it must be a human!
… A whole lot of humans are failing a reverse turing test, just, fundamentally.
atopi@piefed.blahaj.zone 2 weeks ago
it is made to copy how humans write and speak
the AI had been scored for how good it learned from humans to sound sorry
fruitycoder@sh.itjust.works 2 weeks ago
If anything its context includes that it makes mistakes now and details about them. The mostly output is to create the same mistakes again
cv_octavio@piefed.ca 2 weeks ago
It doesn’t even want to ignore the rules. It doesn’t want anything. Just some math didn’t work out and a thing happened that wasn’t supposed to. It will absolutely happen again if it maths that way again too.
Zwuzelmaus@feddit.org 2 weeks ago
If only some people meant it that way too!