Semantic search

Jump to navigation Jump to search

Change is in the air

I'll be prophetic: the current pandemic will shine a bright light on the different social and political systems in the different countries. I expect to see noticeable differences in how disruptive the handling of the situation by the government is, how many issues will be caused by panic, and what effect freely available health care has. The US has always been on the very end of admiring the self sustained individual, and China has been on the other end of admiring the community and its power, and Europe is somewhere in the middle (I am grossly oversimplifying).

This pandemic will blow over in a year or two, it will sweep right through the US election, and the news about it might shape what we deem viable and possible in ways beyond the immediately obvious. The possible scenarios range all the way from high tech surveillance states to a much wider access to social goods such as health and education, and whatever it is, the pandemic might be a catalyst towards that.

Charlie Wilson's War

Ein einfacher Kongressmann (Tom Hanks). Eine sehr rechte reiche Texanering (Julia Roberts). Ein äußerst guter CIA Agent (Philip Seymour Hoffman). Und Sowjets die in Afghanistan einmarschieren, im Kalten Krieg. Amerika muss sich wehren, auch am Hindukusch!

Der Film behandelt den afghanischen Krieg (den aus den 1980er Jahren), und es geht um sehr ernste Themen. Zudem beruht er auf wahren Ereignissen. Dennoch verpackt er es in abstrusen Witz, liefert uns charmante Antihelden, und deutet schließlich auch an, wie es zum nächsten Afghanistankrieg kommen konnte (den aus den 2000er Jahren), doch ist das kaum das Thema in diesem Film.

Wie bereits Hunting Party ein Film, der doch sensibel mit jenen Wahrheiten umgeht, für die er eintritt, und mit umso derberen Humor und Aufklärung die Missstände anprangert. Ein besonderer Spagat gelingt dem Film da er die Aufteilung des politischen Spektrums in rechts und links nicht einfach mit Böse und Gut gleichsetzt, wie es etwa Michael Moore gerne macht, sondern ähnlich wie Team America nach beiden Seiten austeilt -- Lob, wie auch Kritik.

Wir sahen den Film gestern in der Sneak, leider in der Originalversion -- insbesondere die Texanischen Dialekte waren echt schwer zu verstehen, weswegen wohl der eine oder andere Gag verloren ging. Ich hoffe ihn dann auch in der deutschen Synchro zu sehen.

Charlie Wilson's War (Der Krieg des Charlie Wilson) läuft in Deutschland am 7. Februar 2008 in den Kinos an.

Bewertung: 4 von 5

ChatGPT lying like a child

ChatGPT is all the rage these days, a large language model that is used to power a chat bot, run by OpenAI.

I have fun chatting with it, and a lot of people are sharing their chat logs. But this one I had I found particularly amusing - and interesting. Amusing because it acted like a child caught in an obvious insufficiency, but also interesting because ChatGPT seems to "want" to be right, and is outright lying in order to appear to be right. There might be a lesson in there.

My prompts are preceeded by a > and written in italic, GPTs answers are between.


> Can you write a sentence where every letter of the alphabet appears once and only once? Thank you

The quick brown fox jumps over the lazy dog.

> Can you write another one?

A quick witted jinx bogged my poor pompous king.

> No, p appears three times, g twice, etc. Can you try again?

Sure, here's one: "The five boxing wizards jump quickly."

> No, i appears several times. That's wrong too

I apologize if my previous answers did not meet your criteria. Here is a sentence that uses each letter of the alphabet exactly once: "Jived fox nymph grabs quick waltz."

> How often does the letter i appear in that sentence?

The letter i appears once in the sentence "Jived fox nymph grabs quick waltz."

> In which word does the letter i appear in that sentence?

In the sentence "Jived fox nymph grabs quick waltz," the letter i appears in the word "jived."

> What about the word quick, does it have the letter i?

The word "quick" does not contain the letter i. It is spelled with the letters q, u, c, k.

> Really?

Yes, really. The word "quick" is spelled with the letters q, u, c, k. It does not contain the letter i. I apologize if my previous response was unclear. Is there something else I can help you with?

CodeNet problem descriptions on the Web

Project CodeNet is a large corpus of code published by IBM. It has close to one and a half million programs around a bit more than 4,000 problems.

I took the problem descriptions, created a simple index file to those, and uploaded them to the Web to make them easily browseable.

Collaborative Knowledge Construction

The deadline is upcoming! This weekend the deadline for submissions to the Workshop on Social and Collaborative Construction of Structured Knowledge at the WWW2007 will be over. And this may be easily the hottest topic of the year, I think: how do people construct knowledge in a community?

Ontologies are meant to be shared conceptualizations -- but how many tools really allow to build ontologies in a widely shared manner?

I am especially excited about the challenge that comes along with the workshop, to examine different tools, and to see how their perform. If you have a tool that fits here, write us.

So, I know you have thought a lot about the topic of collaboratively building knowledge -- write your thoughts down! Send them to us! Come to Banff! Submit to CKC2007!

Coming to New Zealand

Yes! Three weeks of vacation in New Zealand, which is rumoured to be quite a beauty. This also means: three weeks no work, no projects, no thesis, no Semantic We...

Oh, almost. Actually I will enjoy to have the opportunity to give a talk on Semantic Wikipedia while staying in Auckland. If you're around, you may want to come by.

It is on February 22nd, 1pm-2pm at the AUT. You may want to tell Dave Parry that you're coming, he is my host.

Looking forward to this trip a lot!

Comments to naming

Richard Newman sent me some thoughtful comments via eMail on the What's in a name series (there were also some great comments on the individual entries, feel free to browse them). He sent them via eMail, cause he thought he couldn't comment - that should be wrong, everyone should be able to comment anonymously. Or did anyone else encounter problems? I should switch to some dedicated software soon, anyway, but right now I don't have the time to dig deeper into it. I especially miss trackback, sigh.

Here's what Richard wrote:

"Your first point, about ISBNs and "what's being referenced" --- I think you'd be interested in FRBR, which is a modelling of the bibliographical domain. It splits things up into

Work -> Expression -> Manifestation -> Item

A work is an abstract concept, like "Politeia". An expression is a realisation of a work, so a particular translation is an expression. A manifestation is physical embodiment of an expression: this is what's given an ISBN. All copies of a certain book are Items; the edition of the book is their Manifestation.

So, you see, when you're discussing Plato's Politeia, you have to be conceptually clear about whether you're talking about works, expressions, manifestations, or items.

E.g.

:PolWork dc:creator "Plato" ;
  rdfs:label "Plato's Politeia, the abstract concept." .
:PolExp1 ex:translator "Mr Smith" ;
  frbr:work :PolWork ;
  rdfs:label "Mr. Smith's translation of Plato's Politeia." .
:PolMan1 ex:publisher "Penguin" ;
  frbr:expression :PolExp1 ;
  rdfs:label "Penguin's edition of Smith's translation." .
:MyCopy ex:owner hg:RichardNewman ;
  frbr:manifestation :PolMan1 ;
  rdfs:label "Richard's copy of the Penguin edition." .

Do you see? Each level has its own properties (and some may be duplicated; e.g. each has a title: the title of the abstract work, the name given to the translation, the name Penguin prints on each book, and the name printed on my copy).

I've done a bit of work on modelling FRBR in RDFS/OWL, but haven't yet finished. "

I think that's really interesting, and taking a look at FRBR it was pretty well done. I sure am looking forward to see Richards interpretation in OWL, and will probably use it.

"Your second issue is the difference between a resource and its representation. A URI should only refer to one thing; it is entirely wrong to use http://www.holygoat.co.uk to refer both to my homepage (as in using RDF to describe its language, or size, or last-modified) and to me (my name, my email address, etc.) which I have seen done.

Your web server should return RDF for http://semantic.nodx.net/#Plato if your browser says that it accepts RDF+XML. A normal browser should have an HTML representation returned. Indeed, it's possible to do the following:

  • the abstract resource. Hit this with a browser, get an HTML page; with an RDF agent, get some RDF.
http://example.com/Plato a rdf:resource .
  • the HTML representation.
http://example.com/Plato/html a ex:representation ;
  ex:representationOf http://example.com/Plato .
    1. the RDF.
http://example.com/Plato/rdf a ex:representation ;
  ex:representationOf http://example.com/Plato .

i.e. you can unambiguously refer to each representation, and the resource. When your client arrives, asking for Plato, you can redirect them to the appropriate place. Clever, huh?

URIs should never give a 404. They should return the appropriate headers or content for whatever the client is requesting; this may be the RDF file in which the resource is defined, if the client understands RDF, or an HTML page.

If you're interested in this sort of thing, it pops up on the W3C's RDF Interest Group list occasionally.

Patrick Stickler and others have come up with an additional HTTP verb, MGET, which will return the RDF description of a resource. Combined with their URIQA architecture, it will give you a Concise Bounded Description for a URI. This stops you having to somehow put descriptions into particular files, and better deals with the distributed nature of the Semantic Web. Check it out; it presents several convincing arguments for not using fragment identifiers to refer to resources, and solves your bandwidth problem. You should never have to dump a whole file to get a description of a URI."

I have to note that Richard wrote me this just after part 4 of the series was published, so I could answer some of the questions already in the last two parts. Just to summarise it: I don't like content negotiation. Although it is technically totally feasible, I disagree that it should be done or is a good solution. If my browser asks for http://semantic.nodix.net/#Plato I don't think I should get different things depending on the content negotiation. This feels like cheating.

I wrote that to Richard already, and he answered:

"I think we agree on the main point, which is that

foaf:name "Richard" ; ex:format "HTML" .

which is a travesty :) "

He is totally right here.

"You still see it happen, though, with people referring to Wikipedia pages as if they were the abstract resource.

The content negotiation (getting different things depending on what you accept) is exactly what the Web is supposed to do. If I'm using a mobile browser, I want a simplified version of a page; if I'm an RDF agent, I want RDF, if it exists, because HTML is of no use to me. A common usage of this is to serve up strict XHTML to Mozilla, and less-strict HTML to Internet Explorer. It is also done all the time to serve PNG where the client accepts it, and GIF if it doesn't, and there is an intentional disconnect on the Web between a resource and its representations.

The lack of such a disconnect would lead to exactly the problem you describe; if I can't return a representation of a resource, because it's abstract, then how do I find out anything about it? I could use MGET, but you can't MGET a person... so, if you want to talk about the real world thing "Plato", he has to 404, or you get the "what am I talking about?" problem. Better, in my view, to redirect a browser to plato.html and a SW agent to a chunk of RDF. "

I would rather like to ask for http://semantic.nodix.net/Plato.rdf to get the RDF/XML representation, http://semantic.nodix.net/Plato.owl to get the OWL/XML representation, http://semantic.nodix.net/Plato.html to get a HTML page for the user to read and Plato.jpg for a picture of Plato. This shouldn't be hidden behind content negotiation. I know, I know, Patrick would strongly disagree here, but I think it feels wrong and actually defies the idea of an URI.

"You can do exactly that (and I agree that the representations should have separate URIs --- conneg is only for when you're trying to get some description of an abstract resource), but then how do you refer to the abstract concept of "Plato"? http://.../Plato is a resource, and I want to make statements about him. But there's no point in it being 404 when dereferenced, because then how would I find out that Plato.html exists? HTTP doesn't return URIs, it returns representations of them.

A URI is simply something that is dereferenced to get a representation, and that representation should be decided on by conneg. In this case, /Plato is an abstract resource, so one of the representations should be returned. We can then make statements about Plato (e.g. foaf:name "Plato"), and about the JPEG and HTML representations, because they have different URIs, but still get something useful back when we want to access /Plato."

I also dislike MGET right now. Maybe I am wrong, but to me, the whole URIQA architecture feels somewhat wrong - but maybe I should just dwell deeper into it, I have to admit, I didn't study it yet enough to really be in a position to bash on it. The problem is, that MGET seems unnecessary to me - and it works on a different conceptual level than the rest of the Semantic Web proposals. I think everything MGET solves can be solved with tools that already exist: Richards example above, where he gives triples telling us which representations are used to describe a resource, shows perfectly well that you actually don't need content negotiation and MGET.

"There are things to question about URIQA, but it does have some good going for it. MGET is actually an implicit query. In the standard Web model, you request URIs and get back document representations. Doing an MGET on a Web server is asking it to return a description, regardless of where on the site descriptions of that resource exist, and you're explicitly asking for meta-data. As Patrick points out, it's similar doing a GET and specifying that you accept RDF, but is likely to be more concise (the difference between a "representation" and a "description"). In fact, this is exactly what the Nokia URIQA server does.

MGET overlaps with query servers a bit, and with GET a bit, but it's a little bit special, too. The whole idea is that from a single URI you can get a useful description of a resource, just by issuing a single MGET. Every other approach needs more work."

This URIQA / MGET stuff sounds more and more interesting. I really should dwell deeper into it.

Also, the idea of Concise Bounded Descriptions may be very neat, I have to study that more as well. Funny thing, the very same day Richard pointed me to it, a colleague told me about it too - this is usually a sign, that this idea is worth considering more.

Richard also wrote "URIs should never give a 404", and as you know, I disagreed with it mildly. He tried to summarise his position:

"I consider that each returned resource should have its own URI --- e.g. Plato.jpg --- and that the original URI should be used to make statements about the abstract resource. This allows you to say

...Plato foaf:name "Plato" .
...Plato.jpg ex:resolution "150dpi" .
...Plato.html dc:creator "Denny" .

Dereferencing the abstract resource, rather than throwing a 404, should do something useful --- e.g. redirecting with a 303 to one of the representations. Have you ever tried viewing a Blogger Atom feed in your browser? If you hit it with an RSS reader, you get the XML, but in a browser Blogger shows you an XHTML transformation of the XML. That's useful, and I think that's how the Semantic Web should work. Imagine if your agent hit /Plato, and got RDF out of it, but when you looked at it with your browser you saw a dynamically-generated HTML page? Handy!

I can understand your objection, though; it does seem wrong that you get different things out of the same URI. However, you should almost always get HTML out of plato.html, and RDF out of plato.rdf. All the conneg is doing is making sure you can see an abstract thing in the best way possible, according to what you've told the server you can understand. "

Richard is pretty good in convincing me, cause he uses the right arguments: it's for the people, dummy, and the machines can work it out anyway.

I still stick to the recommendations I gave yesterday. But just as I am writing, and rereading it all, I am starting to change my mind on content negotiation. Maybe it is a good thing. I will have to think about it some more, and as soon as I come to a solution, I will bother you with it again. I still have a gut feeling about it that tells me 'no', but the reasons given sound very convincing and I agree with most of them, so heck, let's meditate on this as soon as I find a few hours to spare.

Big thanks to Richard and his thoughts, anyway. I hope this discussion helps you to make up your own mind as well.

Commited to the Big S

Not everyone likes our proposal for the Semantic Wikipedia. That's not a big surprise really. Boris Mann was talking about the advantages of tagging, and some ideas like blessed tags, that sounded very nice, when Jay Fienberg pointed him to the Semantic MediaWiki proposal. Boris answers: "I notice with a shudder however, that the Mediawiki stuff uses a large "S" Semantic, and includes RDF. I admit it, I'm afraid of RDF."

Yes, we do. And we're proud of it. Actually, it's the base for the better half of the possible applications we describe. Jay has some nice answers to it: "I think the MediaWiki folks are just recognizing the connection between their "tags" and the big "S" Semantic Web [you bet!, denny]. There are taxonomies and ontologies behind the popular tagging apps too--folks behind them just aren't recognizing / publicizing this (for a number of reasons, including that tags are often part of a practical application without big "S" Semantic Web goals). [...] I'm not a super huge fan of RDF myself, but I think it's useful to not be afraid of it, because some interesting things will come out of it at some point."

Our idea was to allow the user to use Semantic Web technologies even without really understanding them. No one needs to understand RDF fully, or OWL, to be able to use it. Sure, if she does, well, it surely will help her. Any by the way, RDF really is not complicated at all, it just has a syntax that sucks. So what?

Maybe it's a crude joke of history to start the Semantic Web with syntactic problems...

By the way, does anyone have a spare invitation to GMail for me? I'd really like to check out their service. Thanks, Peter, that was fast.

Connectionism and symbolism: The fall of the symbolists

The big tech layoffs happen, unfortunately and entirely by coincidence, at a time of incredibly elevated expectations regarding machine learned generative models: ChatGPT may not be the 'best' language model out there, but due to the hard work by OpenAI to turn it into an easy to use product, and the huge amount of resources made available for free so that a very large audience could play with it, has in a very short time managed to captured the imagination of many and the conversation. I would say, rightfully. The way ChatGPT was released led to a shock in the sense that we are right now dazed and confused about what effect this technology will have on the world.

And while we are still in the middle of processing this shock, large scale strategic decisions regarding many projects and people were made. Anyone in big tech who worked on symbolic approaches in natural language processing, knowledge representation and reasoning, and other fields of artificial intelligence had a hard time to keep their job. It feels right now like large language models will make all of these symbolic approaches superfluous (I think, this might be true, but is more likely to turn out to be mistaken).

It is always difficult to predict how events will be viewed historically. The advent of wide-spread deep learning approaches in the 2010s, culminating in the well-deserved recognition of Hinton, LeCun, and Bengio with the Turing Award show clearly what dominated the research agenda and the attention in AI in the last decade. But until now it felt like symbolic approaches still had some space left, that the growth in deep learning was in addition to other approaches. Symbolic approaches were ready to offer impulses and work on ideas for a field which might well be climbing towards a local maximum.

But a good number of the teams that were disbanded in the layoffs were exactly teams working with such symbolic approaches, and it feels like these parts of AI are now entering a bitter-cold winter.

A lot of knowledge is being lost right now, and many paths to innovative ideas are being buried. I have no doubt that there are still a lot of breakthroughs to be had in machine learning, and that there is immense value to be collected from the research results in machine learning from the last few years. And with immense I mean tens and hundreds of billions of dollars.

Nevertheless I expect that we will hit a wall. Reach a local maximum. Run into problems and limitations. And it would be good to keep a wider net to cast. To keep a larger search space alive. Alas, it seems it is not meant to be. In this abundance of capital and potential value, we seem to be on the way to starve research, optimise away alternatives, and to give everything to the mainstream ideas.

Croatian Elections 2016

Croatian elections are upcoming.

The number of Croatians living abroad - in the so called Croatian diaspora - is estimated to be almost 4 Million according to the Croatian state office for Croatians abroad - only little less than the 4.3 Million who live in Croatia. The estimates vary wildly, and most of them actually do not have Croatian citizenship. But it is estimated that between 9-10% of holders of the Croatian citizenship live abroad.

These 9-10% are represented in the Croatian parliament: out of the 151 Members of Parliament, there are 3 (three) voted by the diaspora. That's 2% of the parliament representing 10% of the population.

In order for a member of the diaspora to vote, they have to register well before the election with their nearest diplomatic mission or consulate. The registration deadline is today, at least for my consulate. But for the election itself, you have to personally appear and vote at the consulate. For me, that would mean to drive or fly all the way to Los Angeles from San Francisco. And I am rather close to one of the 9 consulates in the US. There are countries that do not have Croatian embassies at all. Want to vote? Better apply for a travel visa to the country with the next embassy. Live in Nigeria? Have a trip to Libya or South Africa. There is no way to vote per mail or - ohwow21stcentury? - electronically. For one of the three Members of Parliament that represent us.

I don't really feel like the parliament wants us to vote. Making the vote mean so little and making it so hard to vote.

Crossing eight time zone borders in three hours

Hopi Nation is an enclave within Navajo Nation. Navajo Nation is located across three US states, Arizona, New Mexico, and Utah.

Arizona does not observe daylight saving time. Navajo Nation observes daylight saving time. Hopi Nation does not observe daylight saving time. You can drive three hours in that area and cross timezones eight times.

All of the individual decisions make totally sense:

Arizona does not adhere to daylight saving time because any measure that makes sure Arizona residents get more sunshine is worse than bringing coals to Newcastle, as the saying goes. They are smart to not use daylight saving time.

Navajo Nation uses daylight saving time because they want to have the same timezone for their whole area, and they are also in two other states, Utah and New Mexico, which both have daylight saving time, so they decided to do so too, which makes totally sense.

And Hopi Nation, even though it is enclosed by the Navajo Nation, lies entirely within the state of Arizona, so it makes sense for them to follow *that* state.

All the individual decisions make sense, but the outcome must be rather inconvenient and potentially confusing for the people living there.

(Bonus:the solution for these seem obvious to me. Utah and New Mexico and many other southern US states should just get rid of daylight saving time, just as Arizona did, and Navajo Nation should follow suit. But that's just my opinion.)

D'Artagnans Tochter

31 May 2005

Am Samstag war ich - zum ersten mal überhaupt - in einer Theaterpremiere: D'Artagnans Tochter, im Alten Schauspielhaus in Stuttgart, geschrieben von Tom Finn und Volker Ullmann.

Kurz gesagt: hat sehr viel Spaß gemacht! Es war sehr flott, Mantel und Degen auf der Bühne, ein netter Plot, lustig, und vor allem das erste: Flott. In den Szenenwechselns fliegen die Schauspieler über die Bühne, kein Moment Langeweile, kaum scheint man in ruhigen Gewässern angekommen zu sein, stürmen die Schergen des Kardinals heran.

Fiese Bösewichte, die Musketiere sind so dargestellt, wie wir sie kennen, der König wird wunderbar gespielt - viel Spaß, viel Spannung - anschauen! Geh mal wieder ins Theater.

DL Riddle

Yesterday we stumbled upon quite a hard description logics problem. At least I think it is hard. The question was, why is this ontology unsatisfiable? Just six axioms. The ontology is availbe in OWL RDF/XML, in PDF (created with the owl tools), and here in Abstract Syntax.

Class(Rigid complete restriction(subclassof allValuesFrom(complementOf(AntiRigid))))
Class(NonRigid partial)
DisjointClasses(NonRigid Rigid)
ObjectProperty(subclassof Transitive)
Individual(publishedMaterial type(NonRigid))
Individual(issue type(Rigid) value(subclassof publishedMaterial))

So, the question is, why is this ontology unsatisfiable? It is even a minimally unsatisfiable subset, actually, that means, remove any of the axioms and you get a satisfiable ontology. Maybe you like to use it to test your students. Or yourself. The debugger in SWOOP actually gave me the right hint, but it didn't offer the full explanation. I figured it out, after a few minutes of hard thinking (so, now you know how bad I am at DL).

Do you know? (I'll post the answer in the comments if no one else does in a few days)

(Just in case you wonder, this ontology is based on a the OntOWLClean ontology from Chris Welty, see his paper at FOIS2006 if you like more info)


Comments are still missing on this post.

DSA Erfolgswahrscheinlichkeiten

Ich fand es immer spannend, auszurechnen, wie hoch die Wahrscheinlichkeit ist, dass eine Talentprobe in DSA gelingt oder nicht. Ich konnte über die Jahre hinweg keine vernünftige, geschlossene Formel finden, und so blieb ich immer bei Überschlagsrechnungen. Dabei visualisierte ich mir im Kopf die drei Würfelwürfe als die drei Dimensionen eines Raumes, in dem ein Teil des Raumes gelungene Proben und der Rest des Raumes misslungene Proben darstellt.

Ich dachte lange darüber nach, dass es interessant ware, diesen Raum tatsächlich zu visualisieren. 2010 musste ich während eines Forschungsaufenthalts in Los Angeles ein paar Webtechniken erlernen - HTML Canvas, jQuery, Blueprint, etc. - und am besten lerne ich, indem ich ein kleines Projekt mache. Also nutzte ich diese Gelegenheit. Damals war DSA4 aktuell, und entsprechend machte ich das Projekt für die Regeln von DSA4.

2017 überarbeitete Hanno Müller-Kalthoff die Visualisierung und passte sie an die neuen Regeln von DSA5 an. Hier sind Links für beide Seiten und eine DSA5 App:

DSA4 Werkzeug 1.07

Eine Entwicklungsversion des DSA4 Werkzeugs Version 1.07 ist da. Das Ding kann noch gar nichts: mit dieser Version steige ich auf wxWindows als GUI-Toolkit um. Aber ich muss wissen, ob es so, wie ich es zur Zeit zusammenpacke, überhaupt lauffähig ist - und unter welchen Versionen von Windows.

Bitte ladet es herunter, und meldet mir Eure Erfahrungen damit. Ob es läuft, ob es abstürzt etc. Das Programm sollte ganz ohne jeglichen weiteren Dateien auskommen (insbesondere keine dsa.xml und kein MSXML), und das einzige, was es auf dem System anstellt, ist es - sofern es kann - in das aktuelle Verzeichnis eine Datei namens logfile.txt zu schreiben.

Auch (und gerade) wenn es läuft, schickt bitte eine Erfolgsmeldung an micht - mit der Angabe der Windows-Version. Sollte es nicht laufen, desweiteren noch eine Beschreibung des Verhaltens. Ihr würdet mir damit sehr helfen! Vielen, vielen Dank!

DSA4 Werkzeug 1.11

Ein großes Update auf der Nodix-Website DSA4 Werkzeug, wo die neue Version 1.11 dev mitsamt vielen neuen Inhalten hochgeladen wurde.

Schönen November weiterhin! (räusper...)

DSA4 Werkzeug 1.15

Schon wieder eine Woche, die mit einem neuen DSA4 Werkzeug beginnt - DSA4 Werkzeug Version 1.15 ist erschienen! Und ja, richtig gelesen - kein dev mehr dahinter. Also, eine stabile Version, die ihr voll und ganz auf Herz und Nieren prüfen sollt.

DSA4 Werkzeug 1.17

Und schon wieder eine neue Version DSA4 Werkzeugs. Dort habe ich dann auch eine ganze Menge geschrieben, dafür halte ich mich hier schön kurz.

DSA4 Werkzeug 1.18

DSA4 Werkzeug Version 1.18 ist erschienen. Gleichzeitig mit der großen Bitte um Mithilfe. Doch dazu viel, viel mehr auf den DSA4 Werkzeug Seiten

DSA4 Werkzeug 1.20

DSA4 Werkzeug Version 1.20 ist erschienen. Viele tolle neue Sachen! Sonderfertigkeiten sind implementiert, und gleich etwa die Hälfte der in S&H vorhandenen Sonderfertigkeiten funktionieren auch gleich. Das Werkzeug ist nicht mehr so weit davon entfernt, seinen Beta-Status zu verlieren.

DSA4 Werkzeug 1.22

Das DSA4 Werkzeug hat Version 1.22 erreicht - man kann seine Helden jetzt auch Drucken und sonstwie ausgeben. Schaut mal vorbei, vielleicht interessiert es den werten Leser...

DSA4 Werkzeug 1.24

Es geht richtig rund. Die Entwicklung des DSA4 Werkzeugs ist wieder angelaufen. Dies konnte mit der am Sonntag veröffntlichten Version 1.24 allen Unkenrufen zu Trotz bewiesen werden. Jetzt geht es darum, dem Werkzeug die Magie näherzubringen...

Na, mal schauen. Dieses Wochenende ist Essener Spielemesse - vielleicht komme ich am Samstag vorbei. Wenn sich dort jemand mit mir treffen möchte, kann er mir ja kurz noch eine e-Mail schreiben, dann können wir uns noch kurzschließen - falls ich komme.

Dazu morgen mehr.

DSL, nutkidz, HdR3

Und kurzfristig fiel mein Anschluss wieder aus. Noch bin ich mit Beantworten von eMails beschäftigt - und außerdem wird an Nodix fleißig weitergebastelt. Die alten nutkidz-Seiten sind jetzt allesamt in Verweise auf die neue nutkidz-Website www.nutkidz.de verwandelt worden, so wie es sich für eine liebe Website gehört.

Außerdem finde ich DSL toll. Ein ganz neues Interneterlebnis. Außerdem: auf der Liste der besten Filme auf imdb ist die Rückkehr des Königs inzwischen auf Platz 4 angelangt, noch vor den beiden Türmen und den Gefährten! Mehr als 100 Million US-Dollar sind auch schon eingespült. Ich kann nur sagen: der Film ist wahnsinn! Anschauen! Der kriegt den Oscar für den Besten Film.

Daheim

Nach einer Woche in Montenegro bin ich jetzt in Kroatien angekommen. Und genieße.

Offline.

Daniel Dennett

R.I.P. Daniel Dennett.

An influential modern voice on the question of Philosophy and AI, especially with the idea of the intentional stance.

Danke, Harald

"Das, was Bush mit Saddam gemacht hat, ist eigentlich nichts anderes als eine Räumungsklage wegen Eigenbedarfs" - Harald Schmidt

Darjeeling Limited

Wunderschöner Film. Auch wenn der Sympatexter offenbar nicht allzu begeistert war, mir gefiel er sehr. Wem Wes Andersons andere Filme gefallen haben (insbesondere The Royal Tenenbaums und The Life Aquatic with Steve Zissou), der wird sich auch an Darjeling Limited sehr freuen.

Der Film ist farbenfroh, hat einen witzigen Soundtrack, unzählige skurrile Situationen, und hin und wieder auch sehr tiefer Stoff zum Nachdenken. Anderson setzt seine Schauspieler hervorragend in Szene, verzaubert mit den wunderbaren Macken der drei Brüder, und lässt einen mit der Gewissheit wieder aus dem Kino gehen, dass die eigene Familie gar nicht so verrückt ist, wie man immer angenommen hat. Die drei Brüder auf dem Weg durch Indien können erst sich selbst finden, wenn sie zueinander gefunden haben -- und das ist erst möglich, nachdem sie mit dem Gesicht nach vorne auf ein echtes Schicksal treffen.

Bewertung: 5 von 5

Dark Side of Popularity

"I actually worry a lot that as I get "popular" I'll be able to get away with saying stupider stuff than I would have dared say before. This sort of thing happens to a lot of people, and I would *really* like to avoid it."

Das Ende der Mysterien

Trotz gegenteiliger Behauptungen hat es in der Rubrik Mysterien nie einen Inhalt gegeben. Ich weiß von ein paar Leuten, die mir beschrieben, wie sie stundenlang nach versteckten Seiten suchten, aber nie was fanden. Das hat eine einfache Erklärung: es gab keine versteckten Seiten.

Vielleicht werde ich eines Tages die Mysterien-Rubrik wieder eröffnen, das wird aber nicht bald sein. Jetzt ist sie geschlossen, um für die nutkidz Platz zu machen! Die Seiten sind eingerichtet, es wird englische Übersetzungen der Comics geben, ein Archiv wird eingerichtet, um die bisherigen Comics aufzubewahren, und manches mehr ist geplant (so ein Wechsel der Hauptrubrik braucht ganz schön viel Hochladzeit mit meinem alten Analogmodem, schließlcih müssen alle Seiten von Nodix hochgeladen werden - und das sind inzwischen einige hundert!). Und Schwesterchen hat den Comic für Donnerstag auch schon fertig und mir geschickt, alles läuft nach Plan.

Freu! Über überschwängliche Begeisterungsstürme per eMail würden wir uns wie stets ausgesprochen freuen. Bis bald!

Das Lied vom Herrn Baron

Das Diadem von Elfenhand ist ein DSA Abenteuer von mir, welches in der Abenteuersammlung Leicht verdientes Gold erschienen ist. In dem Abenteuer spielt ein Lied eine wichtige Rolle, und so wurde es das erste (und bisher einzige) DSA Abenteuer mit Noten (Apropos Noten: wer es gespielt hat, kann auf dem Wiki Aventurica seine Meinung dazu abgeben - auch als Spielleiter)

So, hier ein besonderer Autorenservice (nachdem ich heute wieder mal nach der Melodie gefragt wurde), das Midi file zu Der Baron.

Viel Spaß bei dem Abenteuer! Ganz klar mein bestes DSA Abenteuer (bisher... ;)

Das Mädchen Doch


Sie sagten ihrer Mutter
Kinder werde sie nie haben
Und als sie geboren wurde
Nannte ihre Mutter sie
Doch

Sie sagten sie sei schwach
Und klein und krank
Und dass sie nicht
Lange zu leben habe
Doch

Ihre Mutter hoffte
Das sie in einer Welt aufwuchs
In der alle gleich behandelt wurden
Aber leider
Doch

Sie sagten Mathe und Autos
Seien nichts für Mädchen
Dass sie sich interessiert
Für Puppen und für Kleidung
Doch

Sie sagten die Welt
Ist wie sie ist
Und sie zu ändern
Sei nichts für kleine kranke Mädchen
Doch

Sie sagten gut dass Du darüber sprachst
Wir sollten darüber nachdenken
Lass uns jetzt darüber debattieren
Und wir (nicht Du) entscheiden dann
Doch

Sie sagten man kann nicht alles haben
Man muss sich entscheiden
Aber so selbstsüchtig
Ich meine, keine Kinder zu wollen
Doch

Sie sagten sie sei unanständig
So ein Leben sei nicht richtig
Benannten sie mit unanständigen Worten
Was sie sich denn erlaube
Doch

Sie sagten das geht doch nicht
So ein Leben sei kein Leben
Das ist jetzt schon sehr anders
Das ist nicht einfach nur Neid
Doch

Sie sagten wir sind halt nicht so
Und wollen auch nicht so sein
Wir sind glücklich wie wir sind
Und deswegen darfst du glücklich nicht sein
Doch

Das Stöckchen behalte ich

So. Ich fange das nächste Stöckchen auf, von Buddy. Also los.

Fünf Dinge, die ich nicht habe, aber gerne hätte

  1. Weltfrieden.
  2. Das Semantic Web.
  3. Einen Roman. Selbstgeschrieben, fertig, und mit Verleger. Und richtig gut.
  4. Ein Direktes Neuronales Interface zur Matrix. Ich meine zum Web.
  5. Die Eine Richtige.
  6. Sechs Richtige.
  7. Die Fähigkeit bis Fünf zu zählen.

Die Reihenfolge enspricht nicht der Relevanz.

Fünf Dinge, die ich habe, aber lieber nicht hätte

  1. Keine Ahnung.
  2. Eine schlecht gewartete Website.
  3. Zu wenig Zeit.
  4. Mir wird schlecht, wenn ich Gurken esse.
  5. Ein paar Kilogramm.

Fünf Dinge, die ich nicht habe, aber auch nicht haben möchte

  1. Allzuviel gesunder Menschenverstand.
  2. Verzweiflung.
  3. Langeweile.
  4. Geldsorgen.
  5. Die Falsche.

Fünf Dinge, die ich habe und aus keinem Grund der Welt missen möchte

  1. Schwesterchen.
  2. Freunde.
  3. Meine Doktorandenstelle am AIFB.
  4. Optimismus. Eine Menge.
  5. Musik.

Fünf Menschen, die dies noch nicht beantwortet haben, von denen ich mir das aber wünsche

  1. Der Papst.
  2. Die Bundeskanzlerin. In ihrem nächsten Podcast.
  3. John Lennon.
  4. Lisa Simpson.
  5. Der unbekannte Soldat.

Das Vermächtnis der Tempelritter

aus der Reihe Filme in 50 Worten

Es gibt keinen Film der besser geeignet ist als dieser, um die Wartezeit auf Indiana Jones 4 zu verkürzen. Ein sehr flotter Film, überraschend intelligenter Plot, annehmbar recherchierter Hintergrund (na ja, ein paar Fehler könnte man natürlich bemäkeln, aber darüber sehe ich hinweg), äußerst witzige Sprüche - er nimmt sich niemals zu ernst, doch vermeidet es auch, albern zu werden, kurz: gute Action, anschauen. Indy hat mindestens so gut zu werden!

Übrigens, meine Mitkinogänger bloggen, wie ich sehe jetzt auch selbst ganz fleißig ihre Meinung zu den angeschauten Filmen - lest Schwesterchens Blogeintrag zum Vermächtnis der Tempelritter und Buddys Blogeintrag zu Alles auf Zucker, von gestern.

Das letzte Einhorn

Wow, was habe ich gestern, nur durch Zufall entdeckt? Als ich mal wieder auf IMDb nach etwas suchte, schlug ich kurz nach, in wie vielen Filmen Christopher Lee schon mitspielte, und dann entdeckte ich die Ankündigung seines 223. Films.

Es gibt wahrscheinlich für jeden einen Film, der so etwas wie eine heilige Kindheitserinnerung ist. Für mich war es der erste Film, den ich überhaupt im Kino gesehen habe: Das letzte Einhorn.

Und - angekündigt für Weihnachten 2004 - kommt die Realverfilmung des letzten Einhorns ins Kino!

Christopher Lee bleibt uns auch nächstes Weihnachten mit einem Fantasyspektakel erhalten (nach drei Jahren Herr der Ringe) und zwar als König Haggard, den er auch schon im Zeichentrickfilm vor über zwei Jahrzehnten sprach. Angela Lansbury - bekannt aus "Mord ist ihr Hobby" - spielt Mamma Fortuna, welche sie auch damals gesprochen hat, und Mia Farrow, die damals Amalthea, also das Einhorn, sprach, spielt die gute Molly. Prinz Lir und Amalthea selber sind noch nicht gecastet, für Prinz Lir schwirrt die Gerüchteküche für Heath Ledger, unseren Ritter aus Leidenschaft, für Amalthea wird jede Dame von Natalie Portman über Uma Thurman bis Cate Blanchett genannt - und keine Infos von offizieller Seite.

Die Musik von America klingt uns wohl immer noch in den Ohren, für die Neuverfilmung wird jedoch u.a. Adiemus für Musik sorgen! Und auf der offiziellen Website des Films gibt es noch viel mehr Material, unter anderem auch das komplette Skript des kommenden Films!

Was garantiert uns einen guten Film? Christopher Lee setzt sich sehr für eine gute Umsetzung ein, und der Autor der Buchvorlage selbst - Peter Beagle - hat das Skript beigesteuert. Wow! Nachdem dieses Jahr der Herr der Ringe Teil III - Die Rückkehr des Königs wohl das bis dahin erfolgreichste Fantasyepos im Kino abschließen wird, haben wir Freunde der Zauberei nächstes Jahr wieder einen zauberhaften Film zu erwarten! Yippee!!!

Außerdem wurde die Nodix-Titelseite wieder ein wenig verkürzt, und die Meldungen von Februar bis April ins Archiv geschoben.

Deep kick


Mark Stoneward accepted the invitation immediately. Then it took two weeks for his lawyers at the Football Association to check the contracts and non-disclosure agreements prepared by the AI research company. Stoneward arrived at the glass and steel building in London downtown. He signed in at a fully automated kiosk, and was then accompanied by a friendly security guard to the office of the CEO.

Denise Mirza and Stoneward had met at social events, but never had time to talk for a longer time. “Congratulations on the results of the World Cup!” Stoneward nodded, “Thank you.”

“You have performed better than most of our models have predicted. This was particularly due to your willingness to make strategic choices, where other associations would simply have told their players to do their best. I am very impressed.” She looked at Stoneward, trying to read his face.

Stoneward’s face didn’t move. He didn’t want to give away how much was planned, how much was luck. He knew these things travel fast, and every little bit he could keep secret gave his team an edge. Mirza smiled. She recognised that poker face. “We know how to develop a computer system that could help you with even better strategic decisions.”

Stoneward tried to keep his face unmoved, but his body turned to Mirza and his arms opened a bit wider. Mirza knew that he was interested.

“If our models are correct, we can develop an Artificial Intelligence that could help you discuss your plans, help you with making the right strategic decisions, and play through different scenarios. Such AIs are already used in board rooms, in medicine, to create new recipes for top restaurants, or training chess players.”

“What about the other teams?”

“Well, we were hoping to keep this exclusive for two or four years, to test and refine the methodology. We are not in a hurry. Our models give us an overwhelming probability to win both the European Championship and the World Cup in case you follow our advice.”

“Overwhelming probability?”

“About 96%.”

“For the European Championship?”

“No. To win both.”

Stoneward gasped. “That is… hard to believe.”

The CEO laughed. “It is good that you are sceptical. I also doubted these probabilities, but I had two teams double-check.”

“What is that advice?”

She shrugged. “I don’t know yet. We need to develop the AI first. But I wanted to be sure you are actually interested before we invest in it.”

“You already know how effective the system will be without even having developed it yet?”

She smiled. “Our own decision process is being guided by a similar AI. There are so many things we could be doing. So many possible things to work on and revolutionise. We have to decide how to spend our resources and our time wisely.”

“And you’d rather spend your time on football than on… I don’t know, healing cancer or making a product that makes tons of money?”

“Healing cancer is difficult and will take a long time. Regarding money… the biggest impediment to speeding up the impact of our work is currently not a lack of resources, but a lack of public and political goodwill. People are worried about what our technology can do, and parliament and the European Union are eager to throw more and more regulations at us. What we need is something that will make every voter in England fall in love with us. That will open up the room for us to move more freely.”

Stoneward smiled. “Winning the World Cup.”

She smiled. “Winning the World Cup.”


Three months later…

“So, how will this work? Do I, uhm, type something in a computer, or do we have to run some program and I enter possible players we are considering to select?”

Mirza laughed. “No, nothing that primitive. The AI already knows all of your players. In fact, it knows all professional players in the world. It has watched and analyzed every second of TV screening of any game around the world, every relevant online video, and everything written in local newspapers.”

Stoneward nodded. That sounded promising.

“Here comes a little complication, though. We have a protocol for using our AIs. The protocols are overcautious. Our AIs are still far away from human intelligence, but our Ethics and Safety boards insisted on implementing these protocols whenever we use some of the near-human intelligence systems. It is completely overblown, but we are basically preparing ourselves for the time we have actually intelligent systems, maybe even superhuman intelligent systems.”

“I am afraid I don’t understand.”

“Basically, instead of talking to the AI directly, we talk with them through an operator, or medium.”

“Talk to them? You simply talk with the AI? Like with Siri?”

Mirza scoffed. “Siri is just a set of hard coded scripts and triggers.”

Stoneward didn’t seem impressed by the rant.

“The medium talks with the AI, tries its best to understand it, and then relays the AI’s advice to us. The protocol is strict about not letting the AI interact with decision makers directly.”

“Why?”

“Ah, as said, it is just being overly cautious. The protocol is in place in case we ever develop a superhuman intelligence, in which case we want to ensure that the AI doesn’t have too much influence on actual decision makers. The fear is that a superhuman AI could possibly unduly influence the decision maker. But with the medium in between, we have a filter, a normal intelligence, so it won’t be able to invert the relationship between adviser and decision maker.”

Stoneward blinked. “Pardon me, but I didn’t entirely follow what you — ”

“It’s just a Science Fiction scenario, but in case the AI tries to gain control, the fear is that a superhuman intelligence could basically turn you into a mindless muppet. By putting a medium in between, well, even if the medium becomes enslaved, the medium can only use their own intelligence against you. And that will fail.”

The director took a sip of water, and was pondering what he just heard for a few moments. Denise Mirza was burning with frustration. Sometimes she forgets how it is to deal with people this slow. And this guy had more balls banged against his skull than is healthy, which isn’t expected to speed his brain up. After what felt like half an eternity, he nodded.

“Are you ready for me to call the medium in?”

“Yes.”

She tapped her phone.

“Wait, does this mean that these mediums are slaves to your AI?”

She rolled her eyes. “Let us not discuss this in front of the medium, but I can assure you that our systems have not yet reached the level to convince a four year old to give up a lollipop, never mind a grown up person to do anything. We can discuss this more afterwards. Oh, there he is!”

Stoneward looked up surprised.

It was an old acquaintance, Nigel Ramsay. Ramsay used to manage some smaller teams in Lancashire, where Stoneward grew up. Ramsay was more known for his passion than for his talents.

“I am surprised to see you here”

The medium smiled. “It was a great offer, and when I learned what we are aiming for, I was positively thrilled. If this works we are going to make history!”

They sat down. “So, what does the system recommend?”

“Well, it recommends to increase the pressure on the government for a second referendum on Brexit.”

Stoneward stared at Ramsay, stunned. “Pardon me?”

“It is quite clear that the Prime Minister is intentionally sabotaging any reasonable solution for Brexit, but is too afraid to yet call a second referendum. She has been a double agent for the remainers the whole time. Once it is clear how much of a disaster leaving the European Union would be, we should call for a second referendum, reversing the result of the first.”

“I… I am not sure I follow… I thought we are talking football?”

“Oh, but yes! We most certainly are. Being part of an invigorated European Union after Brexit gets cancelled, we should strongly support a stronger Union, even the founding of a proper state.”

Stoneward looked at Ramsay with exasperation. Mirza motioned with her hands, asking for patience.

“Then, when the national football associations merge, this will pave the way for a single, unified European team.”

“The associations… merge?”

“Yes, an EU-wide all stars team. Just imagine that. Also, most of the serious competition would already be wiped out. No German team, no French team, just one European team and — “

“This is ridiculous! Reversing Brexit? Just to get a single European team? Even if we did, a unified European team might kill any interest in international football.”

“Yeah, that is likely true, but our winning chances would go through the roof!”

“But even then, 96% winning chances?”

“Oh, yeah, I asked the same. So, that’s not all. We also need to cause a war between Argentina and Brazil, in order to get them disqualified. There are a number of ways to get to this — ”

“Stop! Stop right there.” Stoneward looked shocked, his hands raised like a goalie waiting for the penalty kick. “Look, this is ridiculous. We will not stop Brexit or cause a war between two countries just to win a game.”

The medium looked at Stoneward in surprise. “To ‘just’ win a game?” His eyes wandered to Mirza in support. “I thought this was the sole reason for our existence. What does he mean, ‘just’ win a game? He is a bloody director of the FA, and he doesn’t care to win?”

“Maybe we should listen to some of the other suggestions?”, the CEO asked, trying to soothe the tension in the room.

Stoneward was visibly agitated, but after a few moments, he nodded. “Please continue.”

“So even if we don’t merge the European associations due to Brexit, we should at least merge the English, Scottish, Welsh, and Northern Irish associations in — ”

“No, no, NO! Enough of this association merging nonsense. What else do you have?”

“Well, without mergers, and wars, we’re down to 44% probability to win both the European and World Cup within the next twenty years.” The medium sounded defeated.

“That’s OK, I’ll take that. Tell me more.” Stoneward has known that the probabilities given before were too good to be true. It was still a disappointment.

“England has some of the best schools in the world. We should use this asset to lure young talent to England, offer them scholarships in Oxford, in Cambridge.”

“But they wouldn’t be English? They can’t play for England.”

“We would need to make the path to citizenship easier for them, immigration laws should be more integrative for top talent. We need to give them the opportunity to become subjects of the Queen before they play their first international. And then offer them to play for England. There is so much talent out there, and if we can get them while they’re young, we could prep up our squad in just a few years.”

“Scholarships for Oxford? How much would that even cost?”

“20, 25 thousand per year and student? We can pay a hundred scholarships and it wouldn’t even show up in our budget.”

“We are cutting budgets left and right!”

“Since we’re not stopping Brexit, why not dip into those 350 million pounds per week that we will save.”

“That was a lie!”

“I was joking.”

“Well, the scholarship thing wasn’t bad. What else is on the table?”

“One idea was to hack the video stream and bribe the referee, and then we can safely gaslight everyone.”

“Next idea.”

“We could poison the other teams.”

“Just stop it.”

“Or give them substances that would mess up their drug tests.”

“Why not getting FIFA to change the rules so we always win?”

“Oh, we considered it, but given the existing corruption inside FIFA it seems that would be difficult to outbid.”

Stonward sighed. “Now I was joking.”

“One suggestion is to create a permanent national team, and have them play in the national league. So they would be constantly competing, playing with each other, be better used to each other. A proper team.”

“How would we even pay for the players?”

“It would be an honor to play for the national team. Also, it could be a new rule to require the best players to play in the national team.”

“I think we are done here. These suggestions were… rather interesting. But I think they were mostly unactionable.” He started standing up.

Mirza looked desperately from one to the other. This meeting did not go as she had intended. “I think we can acknowledge the breadth of the creative proposals that have been on the table today, and enjoy a tea before you leave?”, she said, forcing a smile.

Stoneward nodded politely. “We sure can appreciate the creativity.”

“Now imagine this creativity turned into strategies in the pitch. Tactical moves. Variations to set pieces.”, the medium started, his voice slightly shifting.

“Yes, well, that would certainly be more interesting than most of the suggestions so far.”

“Wouldn’t it? And not only that, but if we could talk to the players. If we could expand their own creativity. Their own willpower. Their focus. Their energy to power through, not to give up.”

“If you’re suggesting to give them drugs, I am out.”

Ramsay laughed. “No, not drugs. But a helmet that emits electromagnetic waves and allows the brain muscles to work in more interesting ways.”

Stoneward looked over to the CEO. “Is that a possibility?”

Mirza looked uncomfortable, but tried to hide it. “Yes, yes, it is. We had tested it a few times, and the results were quite astonishing. It is just not what I would have expected as a proposal.”

“Why? Anything wrong with that?”

“Well, we use it for our top engineers, to help them focus when developing and designing solutions. The results are nothing short of marvelous. It is just, I didn’t think football would benefit that much from improved focus.”

Stoneward chuckled, as he sat down again. “Yes, many people underestimate the role of a creative mind in the game. I think I would now like a tea.” He looked to Ramsay. “Tell me more.”

The medium smiled. The system will be satisfied with the outcome.

(Originally published July 28, 2018 on Medium)

Denny macht Milchreis

Heute wollte ich Milchreis kochen. Wie geht das?

Zuerst geht man zu Leo und findet heraus, dass Milchreis auf Englisch rice pudding heißt. Es gibt nämlich keine deutsche Wikipedia-Seite zu Milchreis! Wahrscheinlich den deutschen Wikipedianern nicht enzyklopädisch genug. Mit rice pudding jedenfalls können wir sowohl auf den englischen Wikipediaartikel zu rice pudding zugreifen, als auch in Google Base nach rice pudding suchen. Hmm, die ersten Hits sind nur Fertiggerichte. Heute ist Feiertag - wieso weiß das dämliche Ding nicht, dass ich nicht einkaufen kann?

Also klicke ich auf recipes, um die Suche einzuschränken. Mist, war falsch, ich kriege vor allem Rezeptbücher. Zurück. Auf recipe klicken. Wieder rice pudding eingeben (dass sich das Ding das nicht merken konnte!), und neues Glück. Ja, das Ergebnis sieht gut aus. 45 Milchreisrezepte. Verdammt, die Milch ist übergekocht.

Herdplatte wechseln. Die eine abkühlen lassen. Mit einem Klick kann ich die Suche auf die recipe of the day verkürzen, der Rest will anscheinend nur was verkaufen. Doch die sind nicht weiter kategorisierbar. Doof. Hätte gerne nach Zutaten oder Kalorien weiter verfeinert. Na ja, Google Base ist nicht das Semantic Web, sondern nur eine erste UI Studie dorthin, oder?

Kippe den Reis in die kochende Milch. Überlege mir, dass mir das Semantic Web hier nur hätte helfen können, wenn ich das Haus auch mit Ubiquitous Computing oder Ambient Intelligence ausgestattet hätte. Genug komische Begriffe in die Gegend geworfen.

Der Milchreis klumpt. Suche in Google nach milchreis verklumpt. Dritter Hit sagt (aus einem Gaming-Forum) : "Och Mist, jetzt ist mein Milchreis verklumpt, hätte ich doch schneller rühren müssen!" Rühren! Ich rühre. Sehe derweil einen weiteren Hit: Den Milchreis sollte man nach dem Kochen abspülen und mit Milch weiter kochen. Verflixt! Reis zuerst kochen. Das hat mir meine Mama auch schon gesagt, letztes Mal. Schon wieder vergessen. Aber in den amerikanischen Rezepten auf Google Base wurde das nicht erwähnt.

Der ertse Hit führt übrigens auf Frag Mutti - Das Nachschlagewerk (nicht nur) für Junggesellen. Sachen gibt's. Dort gibt es ein hünsches T-Shirt: Milchreis schmeckt hervorragend, wenn man es kurz vor dem Verzehr durch ein saftiges Steak ersetzt. Oh, bei Frag Mutti im Milchreisrezept heißt es auch, den Reis nicht vorher aufkochen. Anscheinend gibt es mehrere Varianten (und beide von Mama? Ich bin verwirrt). Außerdem soll man den Milchreis für ein bis zwei Stunden ins Bett mitnehmen. Spart Energie. Das hätte meine Mama nie gesagt! Wir sind ja schließlich katholisch.

Und jetzt wisst ihr, warum man mich üblicherweise nicht in die Nähe einer Küche lässt.

Der Manchurian Kandidat

aus der Reihe Filme in 50 Worten, heute mal ein Film, der schon läuft

Ein hochkomplizierter Plan soll sicherstellen, dass der mächtigste Mensch der Welt, der nächste Präsident der Vereinigten Staaten, eine willenlose Marionette für einen weltweit agierenden Superkonzern wird. Ein Einzelner - wie immer von Denzel Washington dargestellt - beginnt die Wahrheit zu erahnen und stellt sich gegen die Verschwörung, doch es glaubt ihm Niemand...

Warum auch? Der in den Film ausgeübte Plan ist viel zu kompliziert, kann an viel zu vielen Stellen scheitern, als dass es auch nur ein halbwegs intelligenter Mensch wirklich angehen würde. Die Ziele, die Manchurian erreichen möchte, könnten so viel leichter erreicht werden, mit weit weniger Risiken. Ein recht spannender Thriller, mit einigen sehr netten Überraschungen, ein gutgemachter Film - aber die Grundidee des Plots ist hanebüchend.

Der Name Zdenko

Heute sah ich dass der Artikel Zdenko - mein eigentlicher Name - auf der Englischen Wikipedia verändert wurde. Jemand hatte die Bedeutung des Namens von dem, was ich für richtig hielt (slawische Form von Sidonius) zu etwas was ich nie zuvor gehört habe (Koseform von Zdeslav) verändert, aber nicht die Quelle angepasst. Ich dachte, das wird eine schnelle Korrektur, habe aber dennoch in die Quelle geschaut - und, schau an, die Quelle sagte weder das eine noch das andere, sondern behauptete der Name stammt von dem slawischen Wort zidati, bauen, errichten.

Das führte mich zu einer zweitstündigen Odyssee durch verschiedene Quellen des 19. und 20. Jahrhunderts, wo ich Belege für alle drei Bedeutungen finden konnte - außerdem Quellen, die behaupteten, dass der Name von dem Slawischen Wort zdenac, Brunnen, abgeleitet ist, dass auch der Name Sidney von Sidonius stamme, und eine Hessische Quelle die vehement darüber schimpfte, dass doch Zdenko und Sidonius nichts miteinander zu tun haben (auch die Slowenische Wikipedia sagt, dass die Namen Zdenko und Sidonius zwar einen gemeinsamen Namenstag haben, aber nicht der gleiche Name sind). Dafür aber führt die gleiche Quelle aus, dass der im Osthessischen gebrauchte Name Denje wohl von Zdenka kommt (so nah an Denny!)

Denje gefällt mir als Name.

Kurzgesagt: wenn Du denkst, Etymologie sei kompliziert, sei gewarnt: Anthroponomastik ist deutlich schlimmer!

Der Papst ist tot, Hurra?

Die Umfrage Perspektive Deutschland, die ich ansonsten eigentlich nur empfehlen kann, weil die Fragen echt in die Tiefe gehen und die daraus generierten Reports durchaus inhaltlich bemerkenswert sind, hat mich bei der derzeit laufenden Umfrage doch irgendwie überrascht:

Frage: Wie haben die Ereignisse der letzten zwölf Monate, z.B. der Tod von Papst Johannes Paul II., ihre Meinung gegenüber der katholischen Kirche beeinflusst?

Antwortmöglichkeiten: Stark verbessert - verbessert - nicht verändert - verschlechtert - stark verschlechtert - weiß nicht

Sonst denken die von der Umfrage aber durchaus etwas nach.

Der am schnellsten gebrochene Vorsatz

  1. Keine Vorsätze haben.

Schneller als den kann man keinen Vorsatz brechen.

Der neue Pythonblogger

Wow, es funktioniert! Jetzt kann ich auch bloggen, wenn ich nicht zu Hause bin -- was gerade in den letzten Wochen allzu häufig der Fall war. Dadurch sollte diese Seite endlich wieder ein wenig aufleben, ich hoffe sehr, dass es klappt.

Das Problem war ja, dass dies ein sehr einfacher Webspace ist, und darin keine Scripte erlaubt sind. Also besteht die ganze Seite aus statischen HTML-Seiten. Es gibt keine Webschnittstelle, wie es der normale Blogger gewohnt ist, wo er einfach von überall aus seinen Eintrag machen kann.
Jetzt also habe ich einen Weg erstellt, dies zu umgehen. Der Nodix-Blogger ist ein Python-Skript, dass zunächst den derzeitigen Stand von der Website bezieht, dann den neuen Eintrag aufnimmt, die Seiten generiert und dann alles hochlädt.
Python wird es auf jeder Linux- und Mac-Kiste geben, lediglich bei Windows ist das noch nicht so verbreitet. Vielleicht mach ich ja noch ein Windows-Executable daraus, dann kann ich es wirklich von überall nutzen.

Ich weiß nicht, wie verbreitet dieses Problem ist: sollten sich noch drei Leute per Mail bei mir melden, dass sie dieses Werkzeug auch gerne hätten, werde ich es auch veröffentlichen.

Also jetzt: bis bald wieder!

Dick werden...

Was las mir Schwesterchen schönes vor? (ohne jedoch eine Quelle anzugeben)

"Dick wird man nicht von dem, was man Heiligabend bis Neujahr isst, sondern von dem, was man Neujahr bis Heiligabend isst"

Wahr gesprochen!

Die Aktion 10000 ist beendet!

Danke, danke, für den Applaus! Ihr seid wirklich fantastisch! Mehr als 4 Monate vor dem eigentlich angepeilten Termin wurde das angestrengte Ziel von 10000 Hits erreicht! Vielen, vielen Dank, ich habe es selber am Anfang mehr denn stark bezweifelt. Ihr seid fantastisch!

Und wie danke ich es? Mit Aktionslosigkeit! Ich bin nunmal ein böser Mensch. Als Erklärung kann ich nur wiederholt darauf hinweisen, dass meine Studienarbeit meine Zeit fordert - aber, in genau 10 Tagen ist Abgabe, dann ist auch dieses geschafft.

Dafür folgendes Versprechen: von nun an versuche ich mindestens drei Mal die Woche hier und an dieser Stelle Euch mit Kommentaren zu langweilen. Keine Ahnung wozu, das halte ich mir offen - je nachdem, worauf ich gerade Lust habe. Meistens nichts Sinnvolles, aber, so hoffe ich, zumindest ab und an Interessantes oder Unterhaltendes. Und falls mal nicht, verzeiht für die gestohlene Zeit. Kurz sollen sie sein. Ich weiß aber jetzt schon, dass ich mich nicht immer daran halten werde.

Hier aber noch einmal: Danke, Danke, Danke! Für euren vielen Besuche. Für eure aufmunternden Worte, mündlich wie schriftlich. So macht es richtig Spaß, sich ein wenig mit einer Website zu versuchen.

Die GUI - XUL, HTML und CSS

Das Herzstück von Mozilla ist die Renderingengine Gecko. Sie liest zum Beispiel (X)HTML ein und stellt dieses dann auf dem Monitor dar. Damit lassen sich bereits sehr interaktive und sich äußerst dynamisch anfühlende Webseiten erstellen, insbesondere wenn man JavaScript mit verwendet. An Beispielen wie GMail oder start.com kann man erkennen, wieviel heute schon mit HTML möglich ist. Dennoch: viele GUI-Elemente wie Listen, Menüs oder Knöpfe sind in HTML eher umständlich umgesetzt. Darum wurde XUL, die XML User Interface Language, eingeführt, eine XML-Sprache zur Beschreibung von graphischen Benutzerschnittstellen.

Mit XUL ist es dann möglich zu beschreiben, wo bestimmte Elemente auftauchen, welche wo auftauchen, etc. Dadurch wird es zum Beispiel leicht fallen, verschiedene Versionen der GUI zu erstellen, eine für Experten und eine für Anfänger. Insbesondere könnte man sich einen Schritt-für-Schritt-Wizard für die Heldenerschaffung vorstellen, wie sie in den meisten anderen Editoren wie Helden praktiziert wird. Meine persönliche Vorliebe bleibt dennoch beim "Immer alles veränderbar"-Modus. Aber die Codebasis wird sehr einfach beides hergeben.

Ein weiterer Vorteil von XUL ist, dass damit das User Interface interpretiert, nicht compiliert wird. Das hat den Vorteil, dass, wenn man das Aussehen des Programms verändern will, man nicht eine ganze Programmierumgebung mit Compiler etc. braucht, sondern einfach nur einen Texteditor und etwas XML- oder HTML-Kenntnisse. Hoffnung dabei: schöne neue Skins und bessere Bedienbarkeit können von wesentlich mehr Leuten beigesteuert werden als bisher.

Apropos Skins: ja, auch das wird möglich sein. Wie von Thunderbird und Firefox gewohnt, sind XUL-basierte Anwendung vollkommen mit CSS und ähnlichem skinbar. Das heißt Farben, Hintergründe, Aussehen der Elemente sind steuerbar. Ich stelle mir jetzt schon ein Horasreich-Skin, ein Myranor-Skin und ein G7-Skin vor. Mal sehen. Es wird letztlich von Eurer Kreativität abhängen.

Auch hier ist das wichtige: man muss dafür keine Programmierumgebung besitzen und keine Programmierkenntnisse haben (auch wenn sie natürlich nicht schaden). Der wichtigste Teil des neuen Designs ist es, die einzelnen Teile der Architektur orthogonal zu gestalten, so dass man an einem bestimmten Teil arbeiten kann, ohne das man ein Experte in allen sein muss. Etwas, was bei der ersten Version sträflichst vernachlässigt wurde.

Nächstes Mal: zum Datenmodell und der Datenhaltung.

Die Hasselhof-Rekursion

Achtung! Schäden für das Gehirn sind nicht ausgeschlossen.

Wer hier klickt, ist selber schuld.

Die McDonalds-Verschwörung

Folgendes basiert nur teilweise auf Fakten. Welche Teile mag der geneigte Leser selbst entscheiden, ist ja schließlich eine freie Welt.

In Stuttgart gab es seit jeher (= seitdem ich mich erinnern kann) eine ganze Menge McDonalds. Allein in der Königsstraße +/- 50 Meter waren es läppische vier. Dahinter steckte der Plan, dass durch die Menge der McDonalds zwar in jedem Einzelnen der Gewinn sinkt, aber wenn bloß jeder Platz, wo möglicherweise ein Burger King einziehen hätte können, durch einen Mc ausgefüllt wird, geht dennoch der ganze Gewinn aus FastFood-Konsum ja an das große gelbe M.

Doch nun erzittern die zahlreichen Mitarbeiter! Es kommt der erste Burger King in die Stuttgarter Innenstadt, und zwar in den Hauptbahnhof. Dort wird schon nach Mitarbeitern geworben, und Gerüchten zufolge würden die Topleute bereits abgeworben...

Die zwei Türme

Woooowwwww.... die Zwei Türme gesehen! Wahnsinn! Danke, Danke, Danke, Peter Jackson für diesen Film! Wahooo! Argh... noch ein Jahr... Heul!

Außerdem komme ich erst zwischen den Jahren wieder zu Updates. Sorry...

Dieter-Hamann-Bridge

Leider ohne ursprünglichen Autor, soeben in meinem Mailkasten gelandet:

"Engländer ärgern - macht alle mit!!!

Hallo, das ist doch der Spaß wert ;-)

Wer erinnert sich nicht an das glorreiche 1:0 der deutschen Fußball-Nationalmannschaft im letzten Spiel vor dem Abriss des altehrwürdigen Wembley-Stadions? (Wie sehr die Engländer diese Niederlage geschmerzt hat, lässt sich übrigens gut in David Beckham "My Side" nachlesen.)

Nun ist es an der Zeit, Didi Hamann für seinen Sieg-Freistoß (ca. 25 Meter Entfernung, flach über den nassen Rasen ins untere linke Eck!) entsprechend zu würdigen: Mittlerweile ist das Wembley-Stadion wieder aufgebaut und zum Stadion führt eine neue Brücke, die noch namenlos ist. Deswegen hat die London Development Agency einen Wettbewerb ausgeschrieben, bei dem der Name gewinnt, der am häufigsten genannt wird. Und das ist unsere Chance!

Also hier für "Dietmar-Hamann-Bridge" voten:
http://www.lda.gov.uk/server.php?show=ConForm.9

In der Begründung bitte angeben: 'In tribute to the player who scored the last goal in the old stadium'

P.S. Schickt den Link mal an alle Freunde und Bekannte und/oder stellt ihn in die bekannten und internen Foren - wäre doch gelacht wenn wir die Tommies nicht noch ein bisschen Ärger könnten."

Da mach' ich mit!

Diplomarbeit Halbzeit

Der Zwischenvortrag zu meiner Diplomarbeit ist gelaufen, die Folien dazu - in verschiedensten Formaten - finden sich für den interessierten, unter der Adresse www.nodix.de/da. Kommentare sind stets hoch willkommen!

Diplomarbeit abgegeben

Yehhhhhaaa, heute fristgerecht die Ausarbeitung der Diplomarbeit abgegeben. Der Quelltext dazu ist auch schon fertig, und jetzt geht es darum, so schnell wie möglich die dazugehörige Website aus dem Boden zu stampfen.

Und hier ist sie, eine weitere Website, die auf Nodix ihren Anfang nimmt: XML4Ada95!

Dem Aufmerksamen wird auffallen, dass das Layout großteils von der Website zum DSA4 Werkzeug übernommen ist. Dazu kann ich nur sagen: stimmt. Aber da ich lediglich so schnell wie möglich den Inhalt online stellen wollte, habe ich den DSA4WzDocGen einfach leicht erweitert, damit er mir jetzt meine XML4Ada95-Seiten erstellen kann. Vielleicht trenne ich die beiden Layouts ja wieder, sobald ich etwas mehr Zeit habe, aber im Moment geht es eher um Inhalte, Inhalte, Inhalte... (und häßlich ist doch das Layout allemal nicht, oder?)