Comment Re: Do they have any business presence in NY? (Score 1) 56
Did not know that. Thanks. But fighting online piracy was only the pretext; the real goal was the usual expansion of government (and thus their) power.
Comment Re: Do they have any business presence in NY? (Score 1) 56
Those illegal narcotics are physically in New York right now. Are the internet servers?
Submission + - A fundamental flaw leaves LLMs strikingly vulnerable to attack (technologyreview.com)
joshuark writes: It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at the International Conference on Machine Learning, a top AI conference, this month. The claim has huge implications for the safety of this technology.
By taking advantage of this flaw, which concerns how LLMs identify who or what is giving them instructions, the researchers were able to make popular LLMs spit out information they had been trained not to provide, such as how to synthesize cocaine and how to sabotage a commercial aircraft’s navigation system.
“There’s a real probability that this is going to be a problem that’s fundamentally unsolvable,” says Charles Ye, an independent researcher and coauthor of the ICML paper.
Companies will typically hire teams of human testers to try to come up with novel attacks that break existing guardrails, a process known as red-teaming. Model makers also use LLM super-hackers (such as OpenAI’s GPT-Red) that find and exploit weaknesses in other models to automate parts of this process. The goal is then to take those attacks and train a new model to resist them and anything that looks like them.
The problem, says Jasmine Cui, another independent researcher and coauthor of the paper, is that the approach amounts to giving the models a list of things they shouldn’t do. But no list is exhaustive. “It’s like watching The Simpsons and they have Bart writing ‘I will not say something inappropriate to my teacher’ a hundred times,” she says. “And he still does things that are pretty crass anyway.”
The ICML paper describes attacks against several of OpenAI’s models, but Cui and Ye say that they have since seen similar results with models made by Anthropic, Alibaba, and DeepSeek.
Cui and her colleagues wanted to find out why an attack like chain-of-thought forgery was so effective. They suspected it had something to do with the mechanism that LLMs use to keep track of where their instructions are coming from.
But what Cui and her colleagues discovered is that LLMs are in fact very bad at keeping track of different roles. In a series of experiments that looked at what was going on inside a handful of different models, the researchers found that LLMs seem to identify the role of a specific chunk of text not by the tags around it but by the style of that text and the words it contains.
The upshot, the researchers claim, is that all an attacker needs to do to hack an LLM is write text that spoofs a certain role. And because roles are a fundamental part of how LLMs work, no amount of training will fully solve the problem.
Ye is worried that nobody is ready for what’s coming. “There’s going to be a huge economic incentive for people to do jailbreaks and prompt injections,” he says. The best defense could be to expect the worst. Organizations shouldn’t trust LLMs, and they should expect that anything done by agents could be unsafe, he says: “That’s not a great solution, but it just might be what we have to do.”
“It’s really incredible that these things are being deployed everywhere to control super-critical systems,” he adds. “There’s been no study of the fundamental science here. We’re all doing it ad hoc.”
By taking advantage of this flaw, which concerns how LLMs identify who or what is giving them instructions, the researchers were able to make popular LLMs spit out information they had been trained not to provide, such as how to synthesize cocaine and how to sabotage a commercial aircraft’s navigation system.
“There’s a real probability that this is going to be a problem that’s fundamentally unsolvable,” says Charles Ye, an independent researcher and coauthor of the ICML paper.
Companies will typically hire teams of human testers to try to come up with novel attacks that break existing guardrails, a process known as red-teaming. Model makers also use LLM super-hackers (such as OpenAI’s GPT-Red) that find and exploit weaknesses in other models to automate parts of this process. The goal is then to take those attacks and train a new model to resist them and anything that looks like them.
The problem, says Jasmine Cui, another independent researcher and coauthor of the paper, is that the approach amounts to giving the models a list of things they shouldn’t do. But no list is exhaustive. “It’s like watching The Simpsons and they have Bart writing ‘I will not say something inappropriate to my teacher’ a hundred times,” she says. “And he still does things that are pretty crass anyway.”
The ICML paper describes attacks against several of OpenAI’s models, but Cui and Ye say that they have since seen similar results with models made by Anthropic, Alibaba, and DeepSeek.
Cui and her colleagues wanted to find out why an attack like chain-of-thought forgery was so effective. They suspected it had something to do with the mechanism that LLMs use to keep track of where their instructions are coming from.
But what Cui and her colleagues discovered is that LLMs are in fact very bad at keeping track of different roles. In a series of experiments that looked at what was going on inside a handful of different models, the researchers found that LLMs seem to identify the role of a specific chunk of text not by the tags around it but by the style of that text and the words it contains.
The upshot, the researchers claim, is that all an attacker needs to do to hack an LLM is write text that spoofs a certain role. And because roles are a fundamental part of how LLMs work, no amount of training will fully solve the problem.
Ye is worried that nobody is ready for what’s coming. “There’s going to be a huge economic incentive for people to do jailbreaks and prompt injections,” he says. The best defense could be to expect the worst. Organizations shouldn’t trust LLMs, and they should expect that anything done by agents could be unsafe, he says: “That’s not a great solution, but it just might be what we have to do.”
“It’s really incredible that these things are being deployed everywhere to control super-critical systems,” he adds. “There’s been no study of the fundamental science here. We’re all doing it ad hoc.”
Submission + - AI Companies Destroying Books At Scale (futurism.com)
nightflameauto writes: AI companies are purchasing books from pre-AI times. The claim is that those books are free from the defects of AI generated text, and therefore more valuable for ingestion into AI datasets. In order to accomplish this, they are tearing the books down to be scanned, then destroying them as the scans are completed. This includes rare and out-of-print books that may be some of the few copies of any given published work left in existence.
Submission + - Is Mark Zuckerberg Actually TRYING to Destroy Meta? (futurism.com)
fjo3 writes: Lately, it almost feels like Zuckerberg is trying to destroy his own company. He’s burning through mountains of cash in a desperate attempt to keep up in the AI race. Yet despite the untold billions it’s spent so far, it’s being destroyed by OpenAI and Anthropic. Its employees have even resorted to using AI models made by its competitors, a humiliating reality check for how far behind Zuckerberg’s efforts have fallen.
It’s also a financial nightmare. Capital expenditures have risen dramatically, erasing any appetite for Meta on Wall Street. Its stock price “has been dead money for more than a year,” as Yahoo Finance notes, as investors continue to debate whether Zuckerberg is chasing the AI industry as it careens off a cliff — or edging ever closer to an AI-fueled industrial revolution.
It’s also a financial nightmare. Capital expenditures have risen dramatically, erasing any appetite for Meta on Wall Street. Its stock price “has been dead money for more than a year,” as Yahoo Finance notes, as investors continue to debate whether Zuckerberg is chasing the AI industry as it careens off a cliff — or edging ever closer to an AI-fueled industrial revolution.
Submission + - The first active shooter suppression service
An anonymous reader writes: Schools to tackle active shooters with pepper-spraying drones that can ram attackers
Pepper-spraying drones aimed at tackling active school shooters are being rolled out at campuses across three states.
The drones, part of the Campus Guardian Angel program, can ram into targets at speeds of up to 70 mph and are capable of weaving through the air to avoid gunfire. Three schools in Florida, five in Georgia and one in Colorado are part of pilot schemes using the aerial technology.
Pepper-spraying drones aimed at tackling active school shooters are being rolled out at campuses across three states.
The drones, part of the Campus Guardian Angel program, can ram into targets at speeds of up to 70 mph and are capable of weaving through the air to avoid gunfire. Three schools in Florida, five in Georgia and one in Colorado are part of pilot schemes using the aerial technology.
Submission + - Your Brain Can Rewire Itself to Allow True Multitasking (sciencealert.com)
alternative_right writes: Our daily lives are built on multitasking, but are our brains actually doing two things at once, or just switching very quickly between them?
Well, it depends. The science shows it's the latter, for cognitively demanding work.
But in a new study published in the Journal of Cognitive Neuroscience, researchers from Georgetown University Medical Center in the US have revealed that we can put certain tasks on autopilot in a way that enables something closer to true multitasking.
Driving is the perfect example: When you take your test, your entire mental and physical energy is concentrated on executing the right combinations of movements and thoughts.
After a decade behind the wheel, the brain is no longer consciously thinking everything through in great detail.
Well, it depends. The science shows it's the latter, for cognitively demanding work.
But in a new study published in the Journal of Cognitive Neuroscience, researchers from Georgetown University Medical Center in the US have revealed that we can put certain tasks on autopilot in a way that enables something closer to true multitasking.
Driving is the perfect example: When you take your test, your entire mental and physical energy is concentrated on executing the right combinations of movements and thoughts.
After a decade behind the wheel, the brain is no longer consciously thinking everything through in great detail.
Comment Re:Big AI's business scheme (Score -1) 38
Copilot: "A million AI tokens costs between half a cent and eight cents in electricity in the U.S., depending on the efficiency of the hardware and the electricity contract."
Can they pay for Operations & Maintenance out of stock sales?
Comment Re: Have to wonder (Score 1) 69
And even if the American buys an American competitor's products to avoid the tariff, the American producers and sellers have room to raise their prices to match the higher foreign prices.
Comment Re:Have to wonder (Score 2) 69
Uh, that's not how tariffs work. Tariffs are paid by importers. The reduced imports would hurt the EU exporters, but the taxes would be paid by Americans.
Comment Re: Why do people keep having kids? (Score -1) 144
How many of my freedoms are restricted due to policies designed to protect ankle-biters?
Comment Re: Why do people keep having kids? (Score -1) 144
Can you please liberalize Kevorkian markets, so I can take the easy way way out without having to hide anything for fear I'll be involuntarily institutionalized again?
Comment Re: Why do people keep having kids? (Score -1, Troll) 144
Will I get banned if I report being a suicidal and bullied kid whom the system really should have weeded out by now but for some depressing reason why am I still here and wouldn't we all be a lot better off if my parents had not succumbed to peer pressure and had me?
Comment Why do people keep having kids? (Score -1, Troll) 144
Do breeders get off on ruining things for the rest of us?
Comment What if authors got a basic income? (Score 1) 64
Would they still write if they got paid $3419 per month, inflation-proofed?
