What should be sex for AI? | Hacker News Reader

What should be sex for AI?

8 pointspiedradura13 comments

Since until now humans are a bad tool to teach a computer how to become intelligent, I wonder if we should try to define what the concept of sex should be for AI. Many hackers many are seduced by new computer languages (like elixir) but perhaps that is not the ideal way of becoming a better programmer.

I envision an ecosystem of machines in which sex is the driving force for evolution, but first we need to define sex for AI. I hope that following this path of evolution human creatures can be seen as sexy by machines and that finally we can produce a new breed.

Edit: Genetic algorithms are not valid in this context since we want an autonomous evolving population, some key ingredient is missing. If someone suggest using genetic algorithm as an initial approach then objective function should evolve with the population in a recursive way, mimicking strategies and resources available in each generation and trying to detect new structures as valuable approach to explore.

Giving software human rights shields authors from responsibility for the actions of their creations.

If I wrote a machine to harass people, I would want my AI to have human rights as well. Then I could claim that it wasn't me who was responsible for harassmaing a human being, but another human being.

In other words, just because you wrote a machine and convinced yourself that it's autonomous shouldn't shield you from responsibility for that machine's actions.

Parents are still liable for any thing and law their children break.

It's an attempt to justify recklessness.

If you know exactly what your machine is going to do, you are responsible for what your machine does. This is why you can have web services.

If you don't know exactly what your machine is going to do, you are unleashing a dangerous machine on an unwitting population of human beings, and that's reckless.

This probably is relevant to the financial sector. Engaging in a digital arms race, and then claiming the machine is responsible for your lost retirement money.

We are so enthralled with technology that we're willing to spend large parts of our lives engaging with it. That's like a teenager loving their bo, damn the consequences.

Now we've come to trust large amounts of other people's money to a digital contest.

Betting large amounts of money on a contest is just that: a bet.

Maybe we should stop and think about whether betting retirement money in a global AI contest is a good idea.

Sure, you can make the argument that gambling is legal in many jurisdictions, but even then you have to remember that the house always wins.

> Giving software human rights shields authors from responsibility for the actions of their creations.

No, it doesn't, in the same way that employees having human rights doesn't prevent employers from vicarious liability for their acts. Or, as its odd you failed to consider given your overstatement of the degree to which parents are liable for children's acts, just as giving children human rights doesn't mean parents can't have responsibility for their harmful actions.

> Parents are still liable for any thing and law their children break.

This is emphatically not true. Parents may be also liable for some subset of their children's torts (e.g., in California, generally only for torts relating to "acts of willful misconduct resulting in death, personal injury, or property damage", and then only up to $25,000 in liability per tort), but they absolutely are not "liable for any thing and law their children break."

Dude...

I am not suggesting physical activity.

Possibly could have phrased it differently.

Also, not sure why a genetic algorithm wouldn't be what you are looking for.

We can't really make "motivations" for the AI stuff we are doing, so making them be "motivated by" reproduction doesn't work,

So, if you just want the ones that fit some task better, that seems like you would just make the more successful ones reproduce more. A genetic algorithm.

I suppose maybe if you had them evaluate each other and have the reproduction be based on that, and have that evolve as well?

But I don't expect that to be a particularly effective training method.

Yes, you suggest a little effective training method. What I suggest is training a lot of very little effective training methods looking for mutations. By not being gready perhaps AI can develop a new system for evolving that we can't envision at this moment.

Just to be a little more concrete: What about a "genetic algorithm" approach for a population in which individuals are genetic algorithms and in which the optimization function put a great weight on being self-sustainability and diversity of structure.

That reminds me of the idea of training a neural net to express a function that, if used where the sigmoid function would be used in a neural net, would result in the neural networks using it being trained well and quickly.

I assumed training a neural net like that would be too expensive (each evaluation of it would require training a neural net), for not much benefit (I don't expect the result to be better than the sigmoid function).

I'm not sure quite what you mean by self-sustainability. What does it mean for a genetic-like algorithm to be self-sustainable?

This idea also sounds like it would be very computationally expensive, but it's possible I misunderstand.

If it could be modified to only use one layer of these algorithms, maybe that would be less expensive?

I am imagining neural nets that each do both image to label, and label to image, where I guess they would engage in a sort of challenge response thing, where one produces a label and requests an image, and evaluates the image received, and provides an image and requests a label (or level of confidence for each label) and evaluates the response, and then when both have evaluated the responses, they output whether or not to reproduce, and if both do, then the genetic part is done. Sort of like a mating dance I guess. (Of course, what challenges and responses they give, and whether they accept, would also be determined by things that are recombined like the other stuff.)

But having that by itself wouldn't be enough, because it needs some connection to real things in order for the "image recognition" to represent anything real. There has to be some sort of real fitness for the reproductive fitness evaluation for the bots to evaluate.

Idk how much that fits with your idea.

The mating dance and the need of some sort of real fitness is interesting. By self-sustainability I was thinking about some form of interactions with the property to not become blocked or extinguished easily, some property to overcome problems, filter agents that don't satisfy certain interesting properties.

the purpose of sex in biological systems is to speed up the rate of genetic change and introduce mutation at a faster rate, there is no reason why Genetic Algorithms couldn't fill this void, OR have two programs collaborate on a set of goals, (i.e. two programs acts as checks and balances for the design of some other program that solves a goal that both parent program understand; (i.e understand not reason about), at that point though, that wouldn't be 'sex', that would just be a collaboration of two programs. Example, two ruby programs get together and write a C program, that in turn could collaborate with the two ruby programs to design and create a 4th program; and perhaps in a different language.)

does this mean i get to fuck robots

I thought from the title it was about gender i.e., how do we assess whether a bot is male / female / neither.

Reply on news.ycombinator.com