I'd pick some Asimov-ish laws if I'd be near step 4, but I'd modify it to include all living beings, not only humans. This is what I've got so far:
The law:* "If realizing an idea makes more negative emotions than without realizing it, don't realize it."* Of course, to put up a law of this level, an AGI system has to dispose with a decent knowledge base. A knowledge base *could* be built without any ethic laws, for a start, but once that a machine becomes enough powerful to make a mess, it means that it is capable of recognizing complex consequences, and the law should be switched on. So basically, what doesn't pass the noted law in a questionized form (if the answer is *"no"*), it doesn't get printed out, or articulated in other mechanical ways. It might be argued whether the noted law would produce a frozen statue effect, but I think it is a good starting point. That was a question about what not to do, but what about the other, "do this" side? In other words, how to generate ideas? I've put a lot of thoughts in this question, and I came up with a simple answer: ideas might be copied from observing living beings. When a bot sees a human answering "yes" to some question, it should answer "yes" to the same question posed to it. Moreover, observed question-answer set should be generalized into functions like *f(question) -> answer* and it would be very tricky to find out what is function *f *composed of, but I think it is achievable. Answers may be in other forms than spoken words, they could be any mechanical articulation that is the machine capable of recognizing and reproducuing in its environment. Function *f* would be the core of machine behavior, it would be build from fragments or wholes of what is seen in the machine environment in particular occasions. Observing multiple possible responses to the same question/command would create a bit of complication, but I guess it could be resolved by noticing different contexts in which the questions/commands are observed. Basically, we can see this kind of behavior in a way infants learn how to do things. They mostly copy behaviors, adjusting some parameters in an intelligent way, to achieve ideas that was born inside their minds, again using imitation mechanism with adjustable parameters. Once we have a resolver of *f *function, all we have to do is to pass it through the law filter. If it passes, an action is performed. And there is another question that opens if the machine surpasses our IQ and even our ethical compassion level: the question of the machine's action credibility. Look at it this way: if a machine (that is a hundred times smarter than you and a hundred times better person than you) advises you to do something, would you listen to it? And in what extent? And what position would that machine deserve in our society? Certainly a lot of interesting questions, but one step at the time, there is a step 3 and 4 to implement. And take a thought on preventing machine unwanted behavior, it might be necessary in the point where machine surpasses us by intelligence. Ivan V. 2018-02-23 21:30 GMT+01:00 Linas Vepstas <linasveps...@gmail.com>: > On Fri, Feb 23, 2018 at 11:26 AM, Amirouche Boubekki > <amirouche.boube...@gmail.com> wrote: > > > >> > The goal of the atomspace is to eliminate human-curated datasets. > >> > >> Music to my ears. "Curated" means "detached from the actual source and > >> context of knowledge." > > > > Not always. Curated means fixed, patched and edited by a human being > > supervisor that knows best, until the correction is delivered in code. > That > > is chance to avoid structural bias like racist bots. > > Ah! Now this last is a very interesting philosophical observation. > This is not quite the correct mailing list within which to discuss > this, but it overlaps onto a large number of political and > mathematical issues that are very interesting to me. So here I go. > > Political - if this was a human, not bot, what amount of racism > should be tolerated? Speech, thought, action are interconnected. For > example: the American constitution enshrines freedom of speech, and > the freedom to practice religion. But clearly, we have lost our > freedom of speech: say the wrong thing about Islam, you get bombed. > Should we restrain freedom of religion? > > Religion is a form of thought. What about freedom of thought? You can > think murderous thoughts, but if you commit murder, you are socially > unwanted (usually). The ability to commit murder is correlated with > the absence of certain neural circuitry in the brain having to do with > empathy. Some humans lack these neurons, and thus are prone to be > psychopaths. Those who do have those neurons, and commit (or even > witness) murder end up with PTSD. > > The mathematical issues first arise if you think of bots as > approximating humans. Its trivial to create a bot that prints random > dictionary words. Its a bit harder, but not too hard, to create a bot > that spews random dictionary words assembled in grammatical sentences > (just run the random word sequences through a grammar-checker, e.g. > link-grammar, and reject the ungrammatical ones; don't print them. > Since most random word-sequences are not grammatical, this is not > CPU-efficient, so better algorithms avoid obviously-ungrammatical > word-sequences by working at higher abstraction layers). What > Microsoft did was just one single step beyond this: spew random > grammatically correct sentences, using a probability weighting based > on recently heard utterances. The system was too simple, the gamers > gamed the system: trained up the probability weights to spew racist > remarks. > > OK, suppose we can go one step beyond what Microsoft did: spew random > sentences, that are created by means of "logical deduction" or > "reasoning" applied to "knowledge" obtained from some database (e.g. > wikipedia, or from a triple store). This could certainly wow some > people, as it would demonstrate a robot capable of logical inference. > > So: this last is where your comment about "structural bias like racist > bots" starts getting interesting. To recap: > > Step 0: random word sequences > Step 1: random but grammatically correct word sequences > Step 2: random grammatical sentences weighted by recent input <-- the > Microsoft bot > Step 3: grammatical sentences from random "logical inferences" <-- > what opencog is currently attempting > ... > Step n: crazy shit people say and do > ... > Step p: crazy shit societies,cultures and civilizations do > > What are the values of n and p? Some might argue that perhaps they > are 4 and 5; others might argue that they are higher. > > My point is: a curated database might make step 3 simpler. Its > hopeless for step 4. > > For a commercial product, curated data is super-important: Alexa and > Siri and Cortana are operating at the step 2/3 level with carefully > curated databases of capitalist value: locations of restaurants, > household products, luxury goods. > > The Russian twitter-bots, as well as Cambridge Analytica and the > Facebook black-ops division are working at the step 2/3 level with > carefully curated databases of psychological profiles and political > propaganda. > > Scientists in general (and Ben in particular) would love to operate at > the step 2/3 level with carefully curated databases of scientific > knowledge, e.g. anti-aging, life-extension info. I'm getting old too. > Medical breakthroughs are not happening fast enough, for me. > > So, yes, curated data is vitally important for commercial, political > and scientific reasons. Just that it does not really put us into step > 4 and 5, which are the steps along which AGI lies. The dream of AGI > is to take those steps, without the curated bullshit (racism, > religion, capitalism) that humankind generates, and yet also avoid the > creation of a crisis that would threaten humanity/civilization. > > Linas. > > -- > cassette tapes - analog TV - film cameras - you > > -- > You received this message because you are subscribed to the Google Groups > "opencog" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to opencog+unsubscr...@googlegroups.com. > To post to this group, send email to firstname.lastname@example.org. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit https://groups.google.com/d/ > msgid/opencog/CAHrUA36%2B3wCN%2BF0kRrJkK59-aCNS1UbZ33JGWkj5XJJSMmGP3g% > 40mail.gmail.com. > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to opencog+unsubscr...@googlegroups.com. To post to this group, send email to email@example.com. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CAB5%3Dj6U787_cotD%3Dh0FgcoSBaS3QU0nAppZ2JwmGUETRmpzoZg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.