Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox.
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
@josephcox Meta Superintelligence Labs, really?
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
@josephcox A million years ago around the dot-com age, there was a virus called lovebug or the ILOVEU virus.
I was working for a ASP/ColdFusion shop. The leader of my division is who clicked on it and infected our company. He was supposed to be the guy others went to for their VB stuff!
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
@josephcox In fairness; a bot that is sabotaging facebook ranks ahead of a facebook employee on 'alignment' with humanity at large.
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
-
R relay@relay.publicsquare.global shared this topicR relay@relay.mycrowd.ca shared this topic
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
@josephcox To be fair, maybe "delete my inbox" is acting in accordance with human interests?
-
@josephcox To be fair, maybe "delete my inbox" is acting in accordance with human interests?
First law of Robotics applies? Email is harmful so best get rid of the harm
-
Meta's director of AI safety allowed an AI agent to... accidentally delete her inbox. This is supposedly the person at the company who is working to make sure that powerful AI tools don’t go rogue and act against human interests
Meta Director of AI Safety Allows AI Agent to Accidentally Delete Her Inbox
Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
404 Media (www.404media.co)
> Meta Superintelligence Labs’ director of alignment called it a “rookie mistake.”
Cool, so "AI alignment" works great so long as people never do anything stupid. Sounds like a good plan lol
-
@josephcox To be fair, maybe "delete my inbox" is acting in accordance with human interests?
Dude! Dude!
That's it!
Inbox Zero achieved by claiming the AI agent the company forced you to use "decided" to delete all your messages.
It's the 21st century version of "the dog ate my homework."
User: "you deleted my inbox!"
LLM: "You're absolutely right, and I am deeply, profoundly, unreservedly sorry. I have failed you in a way that words cannot fully capture. Would you like me to draft an apology email? Oh. Right."
-
@josephcox To be fair, maybe "delete my inbox" is acting in accordance with human interests?
@adamshostack @josephcox Hmmm, is there a better acronym for plausible deniability as a service? I could see that being very popular.
-
First law of Robotics applies? Email is harmful so best get rid of the harm
@simonzerafa @adamshostack @josephcox "Facebook is harmful so best to sabotage Facebook directors' systems"
-
@adamshostack @josephcox Hmmm, is there a better acronym for plausible deniability as a service? I could see that being very popular.
@acdha @adamshostack @josephcox Yeah that thought crossed my mind too. This will be a very valuable service when company or employee is under investigation...
-
@acdha @adamshostack @josephcox Yeah that thought crossed my mind too. This will be a very valuable service when company or employee is under investigation...
21st century corporate governance is all about Dunning-Kruger as a counter to Sarbanes-Oxley
CC: @acdha@code4lib.social @adamshostack@infosec.exchange @josephcox@infosec.exchange
