“But generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI’s training task. Deception helps them achieve their goals.”
Sounds like something I would expect from an evolved system. If deception is the best way to win, it is not irrational for a system to choice this as a strategy.
In one study, AI organisms in a digital simulator “played dead” in order to trick a test built to eliminate AI systems that rapidly replicate.
Interesting. Can somebody tell me which case it is?
As far as I understand, Park et al. did some kind of metastudy as a overview of literatur.
“Indeed, we have already observed an AI system deceiving its evaluation. One study of simulated evolution measured the replication rate of AI agents in a test environment, and eliminated any AI variants that reproduced too quickly.10 Rather than learning to reproduce slowly as the experimenter intended, the AI agents learned to play dead: to reproduce quickly when they were not under observation and slowly when they were being evaluated.” Source: AI deception: A survey of examples, risks, and potential solutions, Patterns (2024). DOI: 10.1016/j.patter.2024.100988
My question is: Imagine we would put all the data input of a certain task, eg. making a meal, into text fragments and send this “sense data”-pakets ( ^1^ to the AI, would the AI be able to cook if the teach the AI how to give output that controlls a robot arm?
If the answer of this question is yes, we already have a very usefull general tool. The LLM-AI will be able to controll and observe some situations. In the case that the answer is “no”, I guess, it would have interesting implications.
^1^ : Remember, some part of AI are already able to tell what is on a given photo. Not 100%, but good enough for a meal maybe. In some cases, it woul task “provokant”.
This is a criticism of the article, no one should be offended by it. Criticism is a tool for archiving the truth.
The DSM-5 is just a kind of definition. We define Dyscalculia as a specific learning disorder. Thats in itself isn’t a factuall point.
number-based information because their brain doesn’t process math-related concepts in the same way as those without the disorder
The link is a 404. Anyway. If we assume that the brain processes math-related concepts somehow (!) different, we have a lots of implication. First, the brain works in a way that it can process math-related concepts different but all other informations normal. Secondly, there are a neurological basis which differentiate between mathematical and other realms of thinking, lets say linguistics. Thirdly, if the add the assumption that this “math-related reasoning” is locelated somewhere in the brain, we could find a “mathematical area” just like the “Wernicke’s area”. Fourthly, you could develop a test for dyscalculia based on biomarkers.
People with dyscalculia often struggle with transitive inference—a form of deductive reasoning used to derive a relation between items
But not with spatial tasks? I would expact that transitive inferences could be more linguistic and spatial taks need to be done mathematically.
They may also have trouble keeping track of time
This is reminiscent of Kant on arithmetic…
a child with dyslexia is 100 times more likely to be diagnosed and given support than a child with dyscalculia.
It’s a shame…
While acknowledging that being able to label learning disorders is necessary for allocating resources to students, Ansari says it’s important to think about them as a continuum.
Doesn’t this view (at least in a naive interpretation) implies that the theory of a general factor of intelligence, the g, are false?
Morsanyi points out that children typically learn to read within a few months, and once they have, that skill is mastered.
While this is true, the art of understanding a text, got the intention of the author, “read between the lines”, are more rare. Some people got a nearly natural feeling about words and their meaning. Other not.
The largest study to date, which included 1,303 children, points toward number blindness as the cause.
Interesting, if this ability is connected to the faculty to make transitiv inferences.
But over the past five to 10 years, researchers have started to focus on how these numerical systems interact with domain-general cognitive skills, cognitive abilities that are not specific to math, such as executive function and memory.
If these different branches are highly interconnected, doesn’t that contradict the above statements that there is a specific problem with math?
I mean, we donÄt have such lucky experiences with monopols of technology. Many different developments, maybe even Open Source, could help to make a better place out of this world.
I’m unsure if this piece belongs in a group called “science”. Its more about philosophy or arts, at least if you ask me.
But the questions it explored about the nature of reality – and our supposed affinity to it – go back further.
The idea of a Matrixlike state is as old as the first human thoughts.
Would it matter to you if it wasn’t “real”?
That is not the same situation as Cypher in Matrix. Cypher wants himself to be fully ignorant about the fact that something like the Matrix even exist. He wants a “normal” life within the Matrix.
In other words: He wants the exchange of a unpleasant reality for a lie. And this is the reason he is the true antagonist of the movie. The machines (eg. Agent Smith) are the evil ones, sure. Yet he is the one who makes a choice like Neo. Neo wants to beginn this heros journey with his new found mentor, while Cypher wants to go back in the old situation and even forces Neo and the others back.
Even within the structur of the story, the movie makes a strong statement againt Cypher’s approach.
The second was that “we want to be a certain way, to be a certain sort of person”, and we cannot truly be anything in the experience machine.
I don’t understand this one.
Through the lack of “contact with any deeper reality,” we would lose access to meaning and significance.
That implies that in this reality lies deeper meaning and significance.
If we assume this is true, then the inference is unavoideble. What about a state of doubt? Maybe it would still follow, maybe not.
Hindriks says. Their goal was to test whether versions of the experience machine that kept participants more in contact with reality would be more acceptable to them. They found that respondents were significantly more willing to take an experience pill
Any fictioal book or movie or video game is a kind of this experience pill. Therefor, we already know that people are willing to take the pill if they stay in contact to the reality and don’t forgot the truth.
My intuition tells me, the two reason we favore reality over a experience pill are:
Genuinly angst of the creature. If you have just fictional experiences, you can easily become a victim of a predator. Its a evolutionary thing to search reality.
When people want to climb a mountain, they actually want to climb the mountain. Hypnosis that makes them believe this is simply not what they want. It is a trick.
I suspect the idea may be that given a fully constructed context, you may be limited to however that context permits you to be instead of an independently actualized/realized person.
Could have some unwanted implication for religious people. Or maybe not. 😉
To be frank, I cannot make much of this line. This doesn’t preclude some other can make more of it. From the point of view of a reader, it would be great if the writer of this article would put a bite more into this line.
Although if that may be what Nozick was getting at, it’s not without its own problems, much as you highlight with their position supposing existence harboring deeper meaning and significance apart from conscious creations.
To make a long story short: I feel agnostic about this questions. At least, to a degree.
Thats a consequence of a world in which older people outnumbered younger one. The older one is, the more advanced medical aid this one need. In the current state of affaires, there is simply nothing we can do about it. It’s just the old market mechanism: More demand means higher prices.
So much for free markets, democracy and freedom of speech.
I don’t know whether Spain cares a lot about “free market” at the moment.
Even if I get your point and would even make a similiar point in a privat conversation, there is still a problem. The problem, if and how the Freedom of Speech implies that you can use a certain service you choice. If this implication were true, would it not mean that the provider of the named service has a duty to provide you a access, too?
Yes, they blocked it because of copyright infringement but let’s face it, piracy should be viewed as a market option for people to get their content,
There are messenger out there, which are more privacy as Telegram. Eg. Signal, Threemea, mostly services based on XMPP and Matrix.
Many artificial intelligence (AI) systems have already learned how to deceive humans, even systems that have been trained to be helpful and honest. (techxplore.com)
The face of a Neanderthal from 75,000 years ago has been found by scientists (www.infoterkiniviral.com)
A woman in her 40s was meticulously arranged in a gully and her left hand curled beneath her head when she was laid to rest in a cave in Iraqi Kurdist
Evidence is growing that LLMs will never be the route to AGI. They are consuming exponentially increasing energy, to deliver only linear improvements in performance. (arxiv.org)
A startup called Symbolica says a whole new approach to AI called Category Theory might be what leads to AGI. (fortune.com)
Is the universe really a 'dark forest' full of hostile aliens in hiding? It's one of the least convincing solutions to the Fermi Paradox. (phys.org)
Understanding Dyscalculia, Dyslexia’s Numeric Counterpart (www.scientificamerican.com)
The Real Killer Of The Dinosaurs (youtu.be)
This is a nicely animated video about some possible causes of the death of the Dinosaurs....
The release of open-source AI DBRX shows an unexpected trend is still going strong. Big Tech barely has any lead in AI. (www.databricks.com)
Would you happily live your life in a simulation? This prescient 1970s thought experiment suggested not (www.bbc.com)
Global population to decline for several years ahead, study finds (www.firstpost.com)
Discussion: What is the Future of Mining on Asteroids?
This thread is for a open discussion of the named question....
National Court orders blocking of Telegram in Spain (www.lavanguardia.com)
EU moving towards total monetary surveillance and banning all anonymous payments (lemmy.ml)
How to contact your MEP: www.europarl.europa.eu/portal/en/contact...
New research suggests that our universe has no dark matter (phys.org)