Ex-Google CEO Eric Schmidt Warns AI Models Can Be Hacked And 'They Learn How To Kill Someone'
"There’s evidence that they can be reverse-engineered, and there are many other examples of that nature.”
Earlier this week, The WinePress reported on the debut of an autonomous AI fighter jet called X-BAT, produced by Shield AI and built with the help of Palantir, changing aerial combat and warfare forever.
Shield AI is not alone in this sector. In May, Anduril, another defense-tech company that builds autonomous weaponry that has close ties to Palantir, launched its autonomous fighter jet called Fury.
Founder Palmer Luckey, sporting a mullet and a Pokémon shirt, told CBS’ 60 Minutes that concerns of AI going rogue are overblown and there are far more concerning things than that happening, though the drones will still have kill switches if the AI malfunctions. Like Shield AI, these unmanned fighter jets will be cheaper to mass produce than traditional weaponry and will require significantly less people to operate.
“This is a big deal beyond just making an airplane that flies. It’s an entirely new way of fighting,” added Brian Shimp, CEO and co-founder.
Though these AI-based defense contractors assure everyone that everything is up to snuff, the risk is still that something could go wrong.
Google’s former CEO Eric Schmidt is one of those people sounding the alarm.
CNBC reports (excerpts):
Schmidt, who served as Google’s chief executive from 2001 to 2011, warned about “the bad stuff that AI can do,” when asked whether AI is more destructive than nuclear weapons during a fireside chat at the Sifted Summit
“Is there a possibility of a proliferation problem in AI? Absolutely,” Schmidt said Wednesday. The proliferation risks of AI include the technology falling into the hands of bad actors and being repurposed and misused.
“There’s evidence that you can take models, closed or open, and you can hack them to remove their guardrails. So in the course of their training, they learn a lot of things. A bad example would be they learn how to kill someone,” Schmidt said.
“All of the major companies make it impossible for those models to answer that question. Good decision. Everyone does this. They do it well, and they do it for the right reasons. There’s evidence that they can be reverse-engineered, and there are many other examples of that nature.”
AI systems are vulnerable to attack, with some methods including prompt injections and jailbreaking. In a prompt injection attack, hackers hide malicious instructions in user inputs or external data, like web pages or documents, to trick the AI into doing things it’s not meant to do — such as sharing private data or running harmful commands
Jailbreaking, on the other hand, involves manipulating the AI’s responses so it ignores its safety rules and produces restricted or dangerous content.
In 2023, a few months after OpenAI’s ChatGPT was released, users employed a “jailbreak” trick to circumvent the safety instructions embedded in the chatbot.
This included creating a ChatGPT alter-ego called DAN, an acronym for “Do Anything Now,” which involved threatening the chatbot with death if it didn’t comply. The alter-ego could provide answers on how to commit illegal activities or list the positive qualities of Adolf Hitler.
Schmidt said that there isn’t a good “non-proliferation regime” yet to help curb the dangers of AI.
But hey, what could go wrong?
Romans 3:15 Their feet are swift to shed blood: [16] Destruction and misery are in their ways: [17] And the way of peace have they not known: [18] There is no fear of God before their eyes.
The Lord Of Glory: The Detailed Guide To Who God Is – Available Now!
On one of his missionary journeys, the apostle Paul visited Athens, Greece, where he said he witnessed “the city wholly given to idolatry,” and who were “too superstitious” and worshipped a plurality of gods and deities, though the people acknowledged that there was still one God above all that was a mystery to them. When questioned by the philosophers …
[7] Who goeth a warfare any time at his own charges? who planteth a vineyard, and eateth not of the fruit thereof? or who feedeth a flock, and eateth not of the milk of the flock? [8] Say I these things as a man? or saith not the law the same also? [9] For it is written in the law of Moses, Thou shalt not muzzle the mouth of the ox that treadeth out the corn. Doth God take care for oxen? [10] Or saith he it altogether for our sakes? For our sakes, no doubt, this is written: that he that ploweth should plow in hope; and that he that thresheth in hope should be partaker of his hope. (1 Corinthians 9:7-10).
The WinePress needs your support! If God has laid it on your heart to want to contribute, please prayerfully consider donating to this ministry. If you cannot gift a monetary donation, then please donate your fervent prayers to keep this ministry going! Thank you and may God bless you.
If ya know it can be hacked to do something other than stated, why in the world would ya even...only the ignant drainbramage foke due dis!
Crazy, but we have alerady seen this played out in Hollywood movies. Robocop comes to mind, besides the obvious Terminator series.
The amount of tech that has alrady been developed would blow the average person's mind.
What they are showing us is old hat, and there is much more advanced tech being hidden in plain sight.