“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

As it appears, it refered to: Lehman J, Clune J, Misevic D, Adami C, Altenberg L, et al. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities. Artif Life. 2020 Spring;26(2):274-306. doi: 10.1162/artl_a_00319. Epub 2020 Apr 9. PMID: 32271631.

Very interesting.

“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.

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”.

To be honest, even the human mind has this faculty not in all cases.

What is Category Theory in this conext?

The most dangerous solution to the Fermi paradox is that many things are possible.

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.

Tired light is the flat earth of astrophysics/cosmology.

Does it really say it? Can you please quote the piece?

While I would certainly like to say I understood any of this. This post has not met any rigorous standard of debunking the researchers findings.

Thats not what the posting claimed to be. You missunderstand. Either intentionally or just as a fact.

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:

• 1. 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.
• 2. 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.

When healthcare costs are going up.

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.

Metal meteoroids are mostly iron, which is cheap on Earth and of little use in space.

As far as I understand your point, the mining in space needs a entire new infrastructure and new methodes in terms of metallurgy and all that.

Very pessimistic outlook. While it could be true, we have in fact no information which could make such a inference necessary.

That are good reasons.

But fighting corruption is not a goal I’m ready to pay any prize for.

I’m conflicted: on one hand, fuck telegram

Why this?

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.

Do you think the human brain operate on a similiar base?

“Strong” Sapir-Whorf might be bullshit, but the weak version is worth checking.

Really persuasiv sounding. ;-)

My hypothesis is that the sort of people who’d engage on persuasive bullshit cares less about truth value of the statements, and that’s what giving them a hard time asserting the truth value of what others say.

Hontestly speaking. This viewpoint isn’t completely false. In some contextes, other aspects are more important than just straight up true value. For instances, some people seems to be used to judge a view not on the merit of it’s reasons, but because of the socially consequences which would arise if the view would hold by a lage mayority. Even if we agree that such points should be irrelevant for a rational discussion, we already know that not all discussions are rational.

I really hope this impressiv and “scientific sounding” headline is more than just another example of the named effect. ;-)

In a series of studies conducted with over 800 participants from the US and Canada, the researchers examined the relations between participants’ self-reported engagement in both types of BSing and their ratings of how profound, truthful, or accurate they found pseudo-profound and pseudo-scientific statements and fake news headlines.

Selfreporting. And this 800 participants, where are they from? Students?