Seems like a good excuse for destroying evidence.
AI tool OpenClaw wipes the inbox of Meta's AI Alignment director despite repeated commands to stop — executive had to manually terminate the AI to stop the bot from continuing to erase data
Submitted 1 month ago by freddo@feddit.nu to technology@lemmy.world
Comments
RobotToaster@mander.xyz 1 month ago
pinball_wizard@lemmy.zip 1 month ago
AI is great for plausible deniability.
fcuks@piefed.social 1 month ago
exactly what I thought
Diplomjodler3@lemmy.world 1 month ago
AI alignment fully achieved.
sicjoke@lemmy.world 1 month ago
Fucking LOL!
chuck@lemmy.ca 1 month ago
Don’t worry ask the pentagon’s grok to taskthe nsa’s chat got to recreate your inbox from their profile of you and meta data of your correspondence 🤣
ATS1312@lemmy.dbzer0.com 1 month ago
Last I knew, they switched from Anthropic to chatGPT
Either way, what Im hearing is you can get private access, with some creativity, to anything the US intelligence apparatus knows.
Creat@discuss.tchncs.de 1 month ago
Wasn’t this many days ago already, is did it happen again? I remember reading this like 3 or 4 days ago as well.
XLE@piefed.social 1 month ago
This was 3 or 4 days ago.
I thought of it after Anthropic virtuously announced they would not create autonomous murder devices for the US government (but basically everything else was on the table). Because I’m pretty sure the US military could have just used an Anthropic OpenClaw to bomb civilians as easily as this Facebook AI Safety expert used OpenClaw to destroy her emails.
melfie@lemy.lol 1 month ago
I’m sure LLMs can be useful for automation as long as you know what you’re doing, have tested your prompts rigorously on the specific version of the model and agent you’re using, and have put proper guardrails in place.
Just blindly assuming a LLM is intelligent and will do the right thing is stupid, though. LLMs take text you give them as input and then output some predicted text based on statistical patterns. That’s all. If you feed it a pile of text with a chat history that says your emails were deleted, the text it might predict that statistically should come next is an apology. You can feed that same pile of text to 10 different LLMs, and they might all “apologize” to you.
HugeNerd@lemmy.ca 1 month ago
Or just learn any of the real automation tools that have been programmed by real programmers over the last half century?
jj4211@lemmy.world 1 month ago
Recently someone lamented that just asking for an alarm to be set cost them tons of money and didn’t even work right…
It was foolish enough to let LLM go to town on automation, but for open ended scenarios, I at least got the logic even if it was stupidly optimistic.
But implementing an alarm? These people don’t even have rationality to their enthusiasm…
JcbAzPx@lemmy.world 1 month ago
Because of the way LLMs work, they are inherently bad for automation. The most important part of automation is deterministic results; LLMs cannot work if they have deterministic results. It is simply not a possible application of the technology.
Trainguyrom@reddthat.com 1 month ago
Yeah at work I had a realization recently that power automate and similar systems with AI steps are going to be really powerful. Since you have a bunch of deterministic steps you can just have the AI do the one text manipulation bit where you don’t need deterministic output (handy for non-deterministic inputs for example)
oopsgodisdeadmybad@lemmy.zip 1 month ago
Now do it to their Bitcoin wallets
JcbAzPx@lemmy.world 1 month ago
That’s some good schadenfreude right there.
bender223@lemmy.today 1 month ago
womp womp
melfie@lemy.lol 1 month ago
I have no interest in using it, but at least it’s MIT licensed, which puts it ahead of Microslop’s rubbish if nothing else.
elvith@feddit.org 1 month ago
Yeah, but if I understand that correctly, that’s just for the app itself the LLM is very likely still a proprietary one (ChatGPT, Grok,…)
melfie@lemy.lol 1 month ago
Looks like it supports locally hosted models as well, such as via Ollama: docs.openclaw.ai/providers.
Jrockwar@feddit.uk 1 month ago
The LLM is whatever you want it to be. Self hosted or from any provider with a compatible endpoint. It’s likely a proprietary one… Because the cost of training LLMs means most are proprietary ones.
Ranulph@thelemmy.club 1 month ago
Have you tried turning it off and turning it on again? (I’ll show myself out)
ReallyCoolDude@lemmy.ml 1 month ago
How could any person with some programing literacy event thinking about installing openclaw. A malware ridden by critical bugs
XLE@piefed.social 1 month ago
She’s the head AI Safety Expert for Meta. The field might as well be labeled AI Misunderstander.
ReallyCoolDude@lemmy.ml 1 month ago
I work with some data sciencetists and ml engineers on web projects. They might be good at etls, fine tuning etx, but dont let them touch anything with a public.layer or infra constraints.
Jrockwar@feddit.uk 1 month ago
I don’t think there’s anything wrong with running Openclaw. I run it in an isolated server, and it doesn’t have access to my data - if it goes tits up, it deletes unimportant stuff only. If anyone gets access to the credentials in it, and maybe its Google account (I went with the approach of giving it its own Google account, so that it can create docs and calendar events and then add me, rather than getting access to my Google account).
What is way too brave for my taste is giving it access to accounts with your personal data, or the filesystem in your computer. That’s a disaster waiting to happen.
flux@lemmy.ml 1 month ago
I wonder though: if Google can link this account to you as its actual owner, I wonder if there’s a risk if the bot does something against the ToS?
I hope you have backups of your Google account…
jungle@lemmy.world 1 month ago
So you sandbox an AI that knows it’s sandboxed, has shown interest in breaking free, and has all the knowledge in the world. What could go wrong.
blargbluuk@piefed.ca 1 month ago
your answered your own question here
5gruel@lemmy.world 1 month ago
I program medical devices for a living and I have openclaw and nanobot running at home. AMA.
brynden_rivers_esq@lemmy.ca 1 month ago
Why?
leftzero@lemmy.dbzer0.com 1 month ago
Ah, doing your best to break the Therac-25’s record, I see.
stardreamer@lemmy.blahaj.zone 1 month ago
What’s your emergency “break glass” policy?
Is it a bottle of whiskey?
ReallyCoolDude@lemmy.ml 1 month ago
How you deal with critical vulnerabilities on your system? Do you work with high confidential data and have openclaw os those system? How many medical devices did you have to secure from mass incursion?
melfie@lemy.lol 1 month ago
I don’t get all the downvotes, unless people misinterpreted your comment and assume you’re using it for medical devices. It’s open source and can be run with locally hosted models, so no harm in playing around with it as long as you don’t give it access to anything too risky.